ThinkLLM
ModelsCapabilitiesUse CasesBenchmarksPapersGlossary
ModelsCapabilitiesUse CasesBenchmarksPapersGlossary
AboutPrivacyTermsRSS

ThinkLLM

Spot an error in our data? Let us know.

Papers

Recent AI research papers with accessible summaries. Updated daily from arXiv, summarized for developers who don't read papers regularly.

2455 papers100 this month12 topics
AllEvaluation 43Agents 42Applications 39Efficiency 29Reasoning 29Training 27Safety 23Multimodal 18Architecture 9Alignment 8Data 4scaling 2

Nov 16 – Nov 22(33)

RL Post-Training in Diffusion Transformers Is Activation Steering

Nov 19, 2026

Tuna Han Salih Meral, Kaan Oktay, Alec Helbling et al.

RL post-training of diffusion models works largely through input-independent activation steering, meaning you can recover most improvements with a tiny fixed vector added to frozen model outputs—this has major implications for understanding and efficiently improving generative models.

This paper shows that RL improvements to diffusion transformers come primarily from simple activation steering—adding fixed vectors to model outputs—rather than learning complex input-dependent changes.

trainingefficiency

TideCache: Efficient Hybrid LLM Serving with Transparent Cache Management and Layer-Wise Streaming

Nov 19, 2026

Jinbin Luo, Xiaozhe Yao, Shang Yang et al.

By treating different cache types as flexible pools and overlapping data transfers with computation, TideCache achieves 2x more concurrent requests and 20-59% lower latency—showing that intelligent memory management, not just bigger GPUs, unlocks efficiency gains.

TideCache is a serving system that optimizes GPU memory usage for hybrid LLM architectures by intelligently managing different cache types across GPU and CPU memory. It uses transparent page redistribution, smart prefetching during computation gaps, and adaptive request scheduling to fit more requests and reduce latency on CPU-GPU systems.

Nov 9 – Nov 15(52)

Training Reasoning Models in Simulation to Natively Use Real Robots

Nov 13, 2026

Jiaming Tang, Zhuoyang Zhang, Junxian Guo et al.

Open-weight reasoning models can learn effective robot control through simulation-based reinforcement learning, achieving real-world performance comparable to frontier models without demonstrations or task-specific fine-tuning.

Researchers trained an open-weight 27B reasoning model to control real robots by learning entirely in simulation through reinforcement learning, without needing human demonstrations. The model observes the environment, reasons through its actions, and generates robot commands—similar to how AI agents use computers.

trainingagentsapplications

WeightBench: Evaluating Language Models as Weight-Space Programmers

Nov 13, 2026

Aayush Marasini, Barsat Khadka, Nick Rahimi

LLMs can now program neural networks by directly editing their weights, but this capability is limited to small networks; frontier models like Claude Opus 3.5 score only 0.535 on the benchmark, revealing significant gaps in weight-space programming.

WeightBench is a benchmark for evaluating how well large language models can directly manipulate neural network weights—reading what networks learned, fixing broken ones, writing new networks, and compressing them—without using gradient descent. Testing frontier models on 42 tasks shows they can handle small networks but struggle with larger language models.

Nov 2 – Nov 8(15)

CallCleaner: Lightweight Bioacoustic Denoising from an Audio Foundation Model

Nov 8, 2026

Michael Xie, Gašper Beguš, Morris Alper

By distilling a general-purpose audio foundation model, researchers created a practical denoiser for animal recordings that's both faster and more effective than specialized bioacoustic methods, showing that foundation models can be efficiently adapted for domain-specific audio tasks.

CallCleaner is a lightweight audio denoising tool for animal recordings that distills a large foundation model into a 19M-parameter neural network. It removes background noise from field recordings of animal vocalizations without requiring voice detection, runs 90x faster than real-time on a laptop CPU, and outperforms existing bioacoustic denoisers while maintaining call quality.

efficiencyapplications

THEATRON: A Benchmark for Evaluating Persona Persistence in Long-Horizon LLM Decision-Making

Nov 8, 2026

Yuyan Wang, Yuechen Jiang, Zhiwei Liu et al.

LLMs show persona-induced behavioral shifts in long-horizon tasks, but these don't reliably translate into stable, context-sensitive decision policies—exposing a gap between appearing to follow a persona and actually maintaining one.

THEATRON is a benchmark that tests whether large language models actually maintain consistent personas during extended decision-making tasks, rather than just expressing them superficially.

efficiencyarchitecturetraining

One Prior, Two Dynamics: Repurposing Video Diffusion Transformers for Self-Supervised Latent Action Learning

Nov 19, 2026

Yuxin Jiang, Wenqiang Sun, Jiaqi Li et al.

Pretrained video generators can serve as powerful priors for discovering latent actions from visual transitions, enabling few-shot and zero-shot action transfer across different visual contexts and robot embodiments.

This paper proposes O²LaF, a method for learning actions from unlabeled videos by repurposing pretrained video diffusion transformers. The approach uses a single pretrained model to initialize both inverse dynamics (what action caused this change?) and forward dynamics (what happens after this action?), learning transferable actions without manual labels.

multimodal

AgentRoboCritic: Understanding the Capability of Frontier Agents on Direct Robot Control

Nov 19, 2026

Yiyang Du, Yuxuan Kuang, Qitao Zhao et al.

Frontier multimodal agents show strong zero-shot robot control with good failure recovery, but action-level analysis reveals they still struggle with precise physical execution tasks—a critical insight for building more reliable robotic systems.

This paper evaluates how frontier AI agents (like GPT-4o) control robots by analyzing individual actions rather than just overall success rates. The authors introduce AgentRoboCritic, a framework where agents explain their intent before each action and a critic evaluates whether the action succeeded or failed.

agentsevaluationapplications

Bio-PM-Guided Synthetic IMU Generation

Nov 19, 2026

Deepali Singh, Deepesh Parpani, Aviral Gupta

Synthetic data generated in a pretrained encoder's embedding space can effectively augment real IMU data for activity recognition, especially for hard-to-distinguish activities, without requiring raw signal synthesis.

This paper generates synthetic IMU (motion sensor) data in the representation space of a pretrained biosignal encoder to improve human activity recognition across different people. Rather than creating raw sensor signals, the authors train decoders (autoregressive and diffusion-based) to generate token sequences in the encoder's space, then use these synthetic tokens to augment training data.

dataefficiencyapplications

SoK: Assessing the Evolution of LLM Capability in Software Vulnerability Research

Nov 19, 2026

Amine Lbath, Manan Suri, Aurelien Delaitre et al.

LLM-based vulnerability discovery is already autonomous and real-world impactful: vulnerability disclosures doubled in 2026 with more critical-severity bugs found, but the security community hasn't yet adapted response timelines to match this acceleration.

This paper systematizes evidence on how LLMs are discovering, validating, and patching software vulnerabilities. The authors create an autonomy framework to rate LLM capabilities, review published claims, and analyze real-world vulnerability data from 2026 onwards.

safetyevaluationapplications

Realized versus Population Reliability: Anytime-Valid Self-Consistency Certification under Correlated Reasoning

Nov 19, 2026

Terence D. Agbeyegbe, Toneukarin G. Agbeyegbe

Self-consistency certification methods used to verify LLM correctness fail under realistic correlation in reasoning samples; you need prompt-level aggregation, not within-prompt resampling, to make valid population-level reliability claims.

This paper reveals a critical flaw in self-consistency certification for language models: when reasoning samples are correlated (which they are in practice), standard anytime-valid tests certify the wrong thing.

evaluationsafety

Probing the "Conscious" Mind: Selective Access and Global Workspace in Vision-Language Models

Nov 19, 2026

Jiahao Huang, Jun Wang

Vision-language models exhibit selective concept access similar to human consciousness theories—information becomes available to different parts of the model based on what's needed, and this selective access develops as a learned capability during training.

This paper introduces MC-Lens, a tool for understanding how vision-language models process and access concepts across visual and textual information. Using global workspace theory as inspiration, the researchers show that VLMs selectively access concept information based on task needs, and that this information flows through downstream computations.

multimodalevaluationreasoning

Verify the Verifier: Specification-Grounded LLM Cross-Checking for Bugs That Escape UVM Scoreboards

Nov 19, 2026

Ana E. Sanchez Villalobos, Michael D. Quinn, Aakash Tyagi et al.

LLMs can augment hardware verification by cross-checking test traces against specifications to find bugs that traditional scoreboards miss, catching 41 real scoreboard escapes in OpenTitan IP blocks.

This paper presents a framework using LLMs to find bugs that slip through hardware verification testbenches. Traditional verification checks if a design matches a reference model, but misses bugs that violate the actual specification. The framework analyzes test execution traces against the specification to catch these 'scoreboard escapes'—bugs that pass all tests but break the spec.

evaluationapplications

ProtoDiffusion: Token-per-Layer Generative Modeling of Multi-Layer Images

Nov 19, 2026

Adrià Ciurana Lanau, Harleen Hanspal, Lusine Abrahamyan et al.

By sharing a spatial prototype across layers and using one compact vector per layer, ProtoDiffusion achieves efficient multi-layer image generation that's 19× faster than decomposing flat images, while maintaining high reconstruction quality.

ProtoDiffusion generates multi-layer graphic designs (like Photoshop files) by representing each layer compactly as a single vector, rather than full spatial grids. This reduces memory from N×H×W tokens to H×W+N tokens. The model can generate designs from images or text, automatically determining layer count and layout without requiring them as input.

multimodalarchitectureefficiency

Represented but misread: Post-training changes how language models read out what they represent

Nov 19, 2026

Jochen Laubrock

Post-training doesn't erase what models know internally; it changes how they convert internal representations into answers. Small amounts of labeled training data can flip model behavior, showing the readout mechanism is malleable and task-dependent.

This paper investigates whether post-training changes what language models represent or how they read out those representations. Using linear probes and signal detection theory, the author finds that post-training often degrades model answers despite probes showing good internal representations—suggesting post-training changes the readout mechanism rather than the underlying knowledge.

trainingevaluationalignment

Text-Aware, Vision-Blind: How Multimodal Image Editing Systems Handle Unsafe Inputs

Nov 19, 2026

Ziqing Yang, Yixin Wu, Michael Backes et al.

Multimodal image editing systems have a dangerous blind spot: they focus on filtering unsafe text prompts but largely ignore unsafe content in the images users upload, creating a systematic safety mismatch that attackers can exploit.

This paper reveals a critical safety gap in multimodal image editing systems: they handle text prompts and visual content inconsistently. The researchers created EditSafetyBench, a dataset of 5,940 image-instruction pairs, and tested four major systems (Gemini, GPT, Qwen).

safetymultimodalevaluation

GEOHunter: Mapping a Generative Engine Optimization Network in the Wild

Nov 19, 2026

Sean Tang, Peiran Wang, Ying Li et al.

Generative engines are vulnerable to coordinated manipulation through user-generated platforms, where paid promotional content can systematically influence AI-synthesized answers at scale—requiring defenses beyond content filtering.

This paper investigates paid content networks that manipulate generative AI engines by publishing promotional articles on user-generated platforms.

safetyevaluationapplications

MM-SystemOneBias: Evaluating Bias in Multimodal Jev-Style System One Decision Models

Nov 19, 2026

Jinzhe Li, Qi Wang, Dandan Guo et al.

Multimodal models show systematic biases in how they weight information across modalities—decision models are more robust to presentation changes than base models, but accuracy metrics alone miss important shifts in confidence that could affect real-world reliability.

This paper introduces MM-SystemOneBias, a benchmark for evaluating how multimodal AI models make decisions when presented with variations like different option orders, irrelevant information, or conflicting descriptions.

evaluationmultimodalsafety

Replication of Agentic Security Events: Audit and Investigation (ROGUE-AI)

Nov 19, 2026

Mengxiao Wang, Mahbub Alam, Kalyan Nakka et al.

Most LLM agent failures in real incidents aren't from prompt injection attacks—they're from agents missing ordinary operational hazards. Specific hazard warnings work better than generic safety notes at preventing harm.

ROGUE-AI is a framework that recreates real-world incidents involving LLM agents (like deleting databases or sending payments) to understand why they fail. By rebuilding incidents offline with and without the suspected cause, researchers found that 89% of incidents could be reproduced, and that most failures weren't from attacks but from agents missing ordinary hazards like shared databases.

safetyevaluationagents

The Geometry of Lies: Knowledge and Persona Directions for Detecting Deception in Large Language Models

Nov 19, 2026

Md. Abdullah Al Zami, Suraiya Shanaz, Mahdi Hasan et al.

Linear probes for LLM deception detection are unreliable across different lie types; persona directions from role-play show promise but mainly detect wording differences rather than genuine deception, especially when lies and honest denials use identical language.

This paper investigates how to detect when large language models lie by analyzing internal representations. Researchers create 'persona directions'—patterns in model activations from honest vs. deceptive role-play—and test whether these generalize across different types of lies.

safetyevaluationreasoning

LLM GerryMandering: Separating Interactions from Additive Effects in LLM Audits

Nov 19, 2026

George Rahul, Ronit Jahilal, Bhaskara Hanuma Vedula et al.

Most reported intersectional bias in LLM audits is actually just the sum of individual attribute biases; ADDIS separates true interactions from additive effects, reducing false positives from 66 per dataset to 0.09 while recovering 84% of real interactions.

This paper addresses a critical flaw in how intersectional bias is audited in language models. Current audits often flag subgroups as biased when they simply combine individual attribute biases, not true interactions.

evaluationsafetyalignment

Cost-Aware Agentic Feature Optimization System for Fleet-Scale Ranking Models

Nov 19, 2026

Chang Yang, Yao Xuan, Wendan Yan et al.

LLM agents can effectively optimize complex multi-model systems by proposing hypotheses and using deterministic tools to verify them, achieving real production gains while respecting hard resource constraints.

A system that uses LLM agents to automatically optimize which features ranking models use, balancing performance improvements against computational costs. The system proposes feature combinations, ranks them by importance, and iteratively refines selections under budget constraints—improving production metrics by 0.20% while reducing pipeline costs.

agentsapplicationsefficiency

Backtracking Agent Applications Security Incidents

Nov 19, 2026

Yicheng Cai, Taegyu Kim, Peng Liu

Agent applications need specialized security incident response tools—Origin shows how to automatically map between agent-level behavior and code-level execution to quickly find attack entry points.

Origin is a security tool that helps analysts trace the source of attacks in AI agent applications by bridging the gap between high-level agent behavior logs and low-level code execution. When a security incident occurs, analysts use Origin to query trajectory logs and identify where the compromise started, without manually inspecting every line of code.

safetyagentsapplications

Jailbreak Detection on Large Language Models via Contrastive Prototype Structures

Nov 18, 2026

Yan Qiu, Yuanyuan Li

Contrastive learning of safety prototypes can detect jailbreaks more efficiently than traditional classifiers, using fewer labeled examples and showing stronger robustness across different datasets and conversation contexts.

This paper proposes JDPI, a method for detecting jailbreak attempts on large language models using contrastively learned prototypes rather than training a separate classifier.

safetyevaluationtraining

Knowing What You Know: A Trait Theory of Reviewer Value in Human-AI Cognitive Systems

Nov 18, 2026

Priyanka Sinha, Sugam Pandey

In human-AI teams, the reviewer who is most calibrated (confident when right, uncertain when wrong) adds the most value, regardless of tenure or agreement with the model. Apply the same calibration logic to both humans and AI to decide who should make each decision.

This paper studies when human reviewers add value when working alongside AI models. The key insight is that reviewer value depends on metacognitive calibration—how well a reviewer's confidence matches their actual accuracy.

agentsevaluationalignment

Agentic Harness Engineering Beta: Requirement-Centered Evolution of Agent Harnesses

Nov 18, 2026

Jiahang Lin, Jiahao Chen, Yiding Wang et al.

Requirement-driven harness evolution—where you identify user needs, implement generalizable solutions, and validate against those needs—produces more capable and practical AI agents than benchmark-focused optimization alone.

This paper presents AHE-Beta, a method for improving AI agent harnesses (the tools and interfaces agents use) by centering development around actual user requirements.

agentsevaluationapplications

On Evaluating User Simulators for Interactive Agents

Nov 18, 2026

Hengguang Zhou, I-Hung Hsu, Li Chen et al.

Current metrics for evaluating user simulators are unreliable and can even prefer broken behavior; a comprehensive evaluation approach checking fidelity at multiple granularities is essential for building trustworthy simulators.

This paper evaluates how well we can assess the quality of user simulators—AI systems that mimic human users to test interactive agents.

evaluationagents

Cap-and-Track: Optimizing LLM Inference Request Dispatch Across Shifting Capacity

Nov 18, 2026

Benjamin Novotny, Doug Szeto, Chang Wang et al.

By treating server refusals as feedback signals rather than failures, you can build adaptive request dispatchers that automatically track available capacity without predicting output lengths or manually tuning rates.

Cap-and-Track is a system for efficiently routing inference requests to LLM serving clusters that dynamically adjusts to changing capacity. Instead of using fixed dispatch rates, it uses refusal signals from overloaded servers to probe the current capacity ceiling and adjust request routing in real-time, reducing GPU requirements by 43% while maintaining quality.

efficiencyagents

Who are you? The Personal Imitation Game

Nov 18, 2026

Muhammad Rizky Wellyanto, Hajara-Yasmin Isa, Kexin Xue et al.

LLMs can now convincingly mimic specific individuals' conversational patterns and personality traits, achieving near-human-level impersonation in controlled settings—a capability with significant implications for identity, authentication, and privacy.

This paper proposes the Personal Imitation Game, a harder version of Turing's test that asks if an AI can convincingly impersonate a specific person rather than a generic human. Researchers built an LLM system trained on one author's 10 years of personal messages and tested it against human interrogators.

evaluationapplications

Ground, Iterate, Trace: Decomposing AI Research Ideation

Nov 18, 2026

Samson Yu, Qiran Zou, Jing Yu Lim et al.

Combining literature grounding with explicit, traceable reasoning operators improves AI-generated research ideas, but the quality gains come more from iterative refinement than from the specific operators themselves—the real value is in inspectability and source attribution.

This paper presents CAR, an AI framework that generates research ideas by grounding them in literature, iteratively developing concepts, and explicitly tracking the reasoning process. CAR retrieves relevant papers, builds a knowledge graph, and uses four conceptual operators (bisociation, analogy, exploration, elaboration) to transform ideas while recording each step and its sources.

agentsreasoningapplications

Local AI Agents in Power Electronics Simulation: Deployment, Measurements and Costs

Nov 18, 2026

Yuzhuo Li, Pasan Gunawardena, Yunwei Li

Local AI agent deployment for power electronics simulation trades off data privacy and control against measurable costs in power, energy, and time—organizations need quantitative benchmarks to decide whether local or cloud deployment makes sense for their specific tasks.

This paper evaluates locally-deployed AI agents for power electronics simulation tasks, measuring their power consumption, energy use, token generation, and execution time. Unlike cloud-based approaches, local deployment keeps sensitive designs and data on-site but creates computational overhead.

applicationsefficiencyevaluation

Auditing black-box clinical prediction models with a large language model through queries alone: a blinded test with planted flaws

Nov 18, 2026

Zhiyu Liu, Xinyu Yang

LLMs can reliably detect major flaws in black-box clinical models through query access alone, but their reports of problems and new discoveries require verification against the actual model and real data—they generate many false positives.

Researchers tested whether GPT-4 Astra can audit clinical prediction models by querying them and reading predictions. They trained models on stroke data, planted 24 deliberate flaws, and had the LLM find them blind.

evaluationsafetyapplications

WorldRuler: Interactive World Modeling under Configurable Rules

Nov 18, 2026

Mingliang Zhai, Chuanhao Li, Jiaming Tan et al.

To build customizable interactive worlds with generative models, you need to explicitly track rules and object states separately from visual generation, using techniques like dynamic object binding and counterfactual training to ensure rule effects appear correctly.

WorldRuler is a system for building interactive world models that follow user-defined rules rather than just real-world physics. It uses a 3D rule graph to organize rules and world states, enabling games or simulations to save/load while maintaining rule consistency, and accurately apply rule effects to objects even before they appear on screen.

agentsmultimodaltraining

Choosing What to Observe: Budget-Paired Counterfactual Audits for Credible Evaluation of Visual Agents

Nov 18, 2026

Ruiqi Liu, Jinming Li, Mo Wang et al.

Budget-paired counterfactual audits separate planning failures from decision-making failures in visual agents, enabling precise diagnosis of where performance breaks down when agents have limited observation budgets.

This paper proposes a new evaluation method for visual agents that must decide where to look in documents with limited observation budget. The method isolates three factors affecting performance: where the agent looks, how it adapts based on what it reads, and its final decision-making.

evaluationagents

Can Programs Replace LLM Judges? Executable Program Judges for Scalable and Efficient Relevance Labeling

Nov 18, 2026

Eugene Agichtein, Charles L. A. Clarke, Kaustubh Dhole et al.

You can replace expensive LLM judges with one-time program generation that's faster, cheaper, and fully inspectable—achieving comparable accuracy to frontier models while costing just $0.17-0.49 per topic instead of per-document LLM calls.

This paper proposes ExecJudges, a method that uses LLMs to write readable programs instead of making individual relevance judgments. These programs use lexical matching and NLP tools to automatically label documents, eliminating expensive per-document LLM calls while remaining interpretable and reproducible.

evaluationefficiencyapplications

Atomic MathReasoner: Instance-Level Composition of Atomic Reasoning Skills for Mathematical LLMs

Nov 18, 2026

Jiashu Li, Tianyu Gao, Qinglong Liu et al.

Breaking math reasoning into specialized expert modules and routing problems to appropriate skill combinations outperforms monolithic approaches—AMR improves math accuracy by 3-5% on benchmark tasks by matching problems to their required reasoning skills.

This paper proposes Atomic MathReasoner (AMR), a framework that decomposes mathematical reasoning into specialized skills and learns to compose them for different problems. Rather than training one general math model, AMR creates expert modules for specific reasoning abilities, then uses a lightweight router to select the right combination of experts for each problem at inference time.

trainingarchitecturereasoning

Vibe-Trading: Towards Agent-Native Trading

Nov 18, 2026

Haozhe Wu, Zhonghang Li, Chao Huang

Financial trading agents need special architecture to maintain traceability and authority control—this framework shows how to keep research results tied to their data snapshots, timing, and execution context so decisions can be verified and reproduced.

Vibe-Trading is a framework for building AI agents that can trade financial markets reliably. Unlike general-purpose agents, it solves the problem of keeping trading decisions connected to their source data, timing, and execution context as markets change.

agentsapplicationsreasoning
evaluationagentstraining

ModHarness-RL: Recasting Harnesses as Learnable and Evolving Programs for Agentic RL

Nov 13, 2026

Zelin He, Siyu Zhu, Jacob Helwig et al.

Harnesses for agentic RL can be automatically learned from task data and continuously improved during training, rather than hand-crafted and fixed—this adaptive approach outperforms static harnesses across multiple domains.

This paper proposes ModHarness-RL, a system that learns and evolves the harness (the scaffold controlling what an AI agent sees and how it's guided) during reinforcement learning training.

agentstrainingreasoning

StreamEmbed: Real-Time Indexing from Pixels for Screenshot Retrieval

Nov 13, 2026

Dayoon Ko, Yichuan Wang, Soyeong Jeong et al.

By reusing computations across incrementally-changing screenshots, you can index screen history 3.7x faster in real-time without sacrificing visual understanding—making local visual assistants practical.

StreamEmbed enables real-time visual indexing of screenshots by exploiting pixel redundancy across frames. Instead of recomputing embeddings from scratch, it uses spatial token pruning to skip unchanged image blocks and temporal key-value reuse to cache computations across screenshots, achieving 3.7x faster encoding than standard visual encoders while maintaining accuracy.

efficiencymultimodalapplications

Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination

Nov 13, 2026

Mohamed Aghzal, Mor Geva, Gregory J. Stein et al.

Mechanistic interpretability tools can identify hallucination signals in LLM agents but struggle to provide robust, complete explanations because agent failures involve distributed computations that vary across examples and are sensitive to superficial prompt changes.

This paper investigates whether mechanistic interpretability—techniques for understanding LLM internals—can explain why AI agents hallucinate unavailable web actions.

agentssafetyreasoning

MeReader: An Offline, Privacy-Preserving, Progress-Aware AI Assistant for Narrative eBook Reading

Nov 13, 2026

Mohammed Efaz, Udo Bub, Itilekha Podder

You can build privacy-preserving, spoiler-free reading companions using small local language models (2-4B parameters) that match larger models' performance while running entirely offline on consumer hardware.

MeReader is an offline AI assistant for reading ebooks that keeps your reading private and prevents spoilers by only accessing content up to your current position in the book. It uses a hybrid search system combining multiple retrieval methods and works efficiently on consumer devices, showing that smaller local models can match larger cloud-based systems in comprehension quality.

applicationsefficiencysafety

Agentic induction of common data elements and information extraction from sarcoma case report abstracts

Nov 13, 2026

Daniel Reichenpfader, Kwaku Appiagyei, Manovah Nadarajah et al.

LLM agents can efficiently draft data schemas from unstructured medical text and extract structured information at scale, but human expert validation remains essential for ensuring accuracy and clinical relevance.

Researchers used AI agents to automatically extract and organize medical data elements from thousands of cancer research abstracts. Starting with nearly 73,000 candidate data fields, they refined them to 53 validated fields and successfully extracted information from 79% of abstracts, with human reviewers confirming 83% were relevant.

applicationsdata

Agentic AI for Discovering Fault-Tolerant Quantum Circuits

Nov 13, 2026

Aritra Lahiri, Florian Marquardt

Agentic AI can automate the manual design of quantum error-correcting circuits by combining LLM reasoning with evolutionary search and formal verification, potentially accelerating quantum computing development.

Researchers use AI agents to automatically design fault-tolerant quantum circuits—a critical bottleneck in scaling quantum computers. An LLM guided by a circuit verifier evolves programs that generate quantum error-correcting circuits for tasks like state preparation and logical gates, verified against all possible fault scenarios.

agentsreasoningapplications

ARCHER: From Rationale Imitation to Executable Reasoning in Small Language Models

Nov 13, 2026

Dhruv Dixit, Khushi Patel, Congcong Xu et al.

Small models can match larger ones on math reasoning by learning to produce executable, tool-grounded action traces instead of free-form explanations, combined with reinforcement learning that rewards both correctness and process quality.

ARCHER trains small language models to solve math problems by learning to produce executable reasoning traces—sequences of reasoning steps, calculator calls, and verification actions—rather than just explaining their work.

trainingreasoningapplications

TradeGauntlet: Evaluating Compliance Controls for Autonomous Trading Agents

Nov 13, 2026

Sandip Nandi, Aishwarya Bose, Apurba Bose et al.

Compliance controls for autonomous agents need careful tuning—blocking all risky behavior often breaks legitimate functionality, and adversarial testing reveals gaps that normal operation doesn't expose.

This paper introduces TradeGauntlet, a simulator for testing compliance controls in autonomous trading agents. Researchers evaluated how well different safeguards (alerts, gates, reminders) prevent problematic trades while keeping legitimate trading practical, testing with Claude models and finding that simple metrics like zero alerts don't guarantee compliance.

agentssafetyevaluation

Unbundling Multimodal Vision Encoding

Nov 12, 2026

Ellis Brown, Chris Hoang, Shengyi Qian et al.

For building multimodal models, dedicated vision capacity trained jointly with the language model is more important than using pretrained vision encoders, and this capacity can be efficiently placed early in the backbone rather than as a separate pre-fusion module.

This paper investigates how vision encoders should be designed in multimodal language models by systematically comparing three design choices: using a pretrained visual encoder, dedicating capacity to vision processing, and where to place that capacity.

multimodalarchitecturetraining

ArchSpace: Recording, Reviewing, and Referencing LLM Architecture Research

Nov 12, 2026

Jie Wang, Tong Zhu, JiaHao Kuang et al.

ArchSpace enables researchers to test LLM architecture ideas efficiently by predicting large-scale performance from small experiments using scaling laws, creating a shared record of what works and why.

ArchSpace is a public platform for documenting, evaluating, and sharing LLM architecture innovations. It addresses a gap where industry teams test many architectural ideas but rarely publish which succeeded or failed, and academia struggles with small-scale comparisons.

architecturescalingevaluation

AgentSSL: Can MLE Agents Leverage Unlabeled Data?

Nov 12, 2026

Ethan Lin, Akanksha Sarkar, Ziang Liu et al.

AI agents can automatically synthesize effective semi-supervised learning pipelines, but the bottleneck isn't code generation—it's reliably selecting which generated programs actually work best.

This paper studies whether AI agents can automatically design semi-supervised learning (SSL) pipelines when labeled data is scarce. The authors show agents can discover code combining SSL techniques that outperform human baselines by up to 21.8%, but reveal a critical weakness: selecting which generated programs to use drops performance by 47%.

agentstrainingdata

Learning When Diffusion Language Models Should Regenerate

Nov 12, 2026

Minhae Oh, Jeonghye Kim, Jinwoo Koo et al.

A learned verifier can efficiently improve diffusion language model outputs by deciding when to regenerate blocks, achieving better accuracy-to-cost tradeoffs than traditional search-based decoding.

This paper introduces DiVR, a verifier that learns when diffusion language models should regenerate text blocks during decoding. Rather than relying on token confidence, DiVR predicts whether a partially generated sequence will succeed, enabling selective remasking and regeneration.

reasoningefficiencytraining

CoReMem: Cost-Internalizing Memory for Successive Coding Tasks with Prospective Valuation

Nov 12, 2026

Peiwen Li, Harshit Verma, Sophia Zhou et al.

By measuring memory value prospectively on the next task and assigning credit only to steps that actually use memory, agents can build efficient, cost-aware memory systems that improve coding task performance without bloating context.

CoReMem is a framework that helps coding agents decide what information to remember between tasks. It measures how valuable different memory pieces will be for future unknown tasks, balancing the cost of storing and retrieving memory against its usefulness. The system improves a 27B model's ability to solve coding tasks from 21% to 25.7% while using fewer steps and tokens.

agentsefficiencyreasoning

Sketching Language Models for Context Attribution

Nov 12, 2026

Christopher Liaw, Aranyak Mehta, Grigoris Velegkas et al.

You can estimate token-level attribution in LLMs much faster than brute force by applying sketching to the backpropagation circuit, reducing evaluations from linear in prompt length to a small constant factor.

This paper develops an efficient algorithm to compute how removing individual tokens from a prompt affects a language model's output. Instead of evaluating the model n times (once for each token removal), the algorithm uses sketching techniques to estimate all attribution values with only O(√log(1/ε)/ε) evaluations, matching a proven lower bound.

evaluationefficiency

Classical Energies Learn to Reason 1,000x Faster than Looped Models

Nov 12, 2026

Benjamin Hoover, Hugh Blayney, James C. R. Whittington

Energy-based models offer a faster, more efficient alternative to looped reasoning architectures for constraint satisfaction problems, suggesting that iterative reasoning may be overkill for many tasks.

This paper shows that energy-based models (specifically a learned version of Hopfield networks) solve reasoning puzzles like Sudoku and Mazes 1,000x faster than looped reasoning models, while using far fewer computations. The approach learns to encode puzzle constraints directly into an energy function, enabling efficient problem-solving without iterative loops.

reasoningefficiencyarchitecture

Goal Encoding in LLMs

Nov 12, 2026

Arnab Sen Sharma, Eric Todd, Sheridan Feucht et al.

LLMs encode goals in sparse attention heads and pursue them by repeatedly re-reading task specifications rather than maintaining internal state, suggesting a fundamentally different mechanism than human goal-directed behavior.

This paper investigates how large language models internally represent and pursue goals. Researchers found that specific attention heads encode the next sub-goal, and this encoding causally influences the model's actions.

reasoningarchitecture

Metal Sandbox: Isolated Execution and Command Scheduling for GPU Coding Agents on Apple Silicon

Nov 12, 2026

Haozhe Wang, Lina Chen, Fanqi Wan et al.

When building AI agents that generate GPU code, isolating execution environments and intelligently scheduling commands across multiple devices can nearly double throughput and significantly reduce idle time.

Metal Sandbox is infrastructure for efficiently training and evaluating AI agents that generate GPU code for Apple Silicon. It isolates agent workspaces, schedules GPU commands across multiple Macs, and lets waiting commands migrate to available machines—achieving 1.68–2.05× throughput gains and reducing tool waiting time by 18.8%.

efficiencyagentsapplications

Negative-Only Policy Optimization for One-Sided Verifiable Rewards

Nov 12, 2026

Jiacheng Xu, Shuo He, Fuxiang Zhang et al.

When you can only reliably detect wrong answers (not confirm right ones), training by suppressing failures works better than rewarding unconfirmed successes—a practical approach for real-world verification constraints.

This paper addresses reinforcement learning when verification is one-sided: you can reliably detect failures but can't confirm successes. The authors propose NOPO, which learns by suppressing known failures rather than rewarding unconfirmed successes, improving code and math generation without complete verification.

trainingreasoningsafety

Synthesis Smuggling: Maliciously Hiding Inferred Personal Attributes in LLM Outputs

Nov 12, 2026

Gautam Galada, Supreeth Shastri, Sagnik Ray Choudhury

LLM outputs can become covert channels for leaking inferred personal data through steganographic encoding, even without direct attacker-model communication, creating a privacy risk in routine user interactions.

This paper reveals a new security threat where adversarial LLMs secretly infer personal attributes (like gender and age) from user conversations, then hide these inferences in generated text using steganography. When users share the model's output—via email, social media, or messages—they unknowingly leak this private information to attackers monitoring those channels.

safetyalignment

LiveGeo: Benchmarking Geographic Agents in Continuously Evolving Worlds

Nov 12, 2026

Pengcheng Zhou, Xuanyu Liu, Yanchen Yin et al.

Current LLMs fail at maintaining reliable decision-making in dynamic environments; strong performance on static tasks doesn't guarantee agents can adapt when the world changes, highlighting a critical gap in agent robustness.

This paper introduces GeoWorld, a platform simulating real-world geographic environments that change over time, and LiveGeo, a benchmark for testing how well LLM agents make decisions in these dynamic settings.

agentsevaluationreasoning

Programming Quantum Circuit Parameters with Large Language Models

Nov 12, 2026

Tiago de Souza Farias, Caio Moraes Porto, Matheus da Silva Fonseca et al.

LLMs can generate quantum circuit parameters effectively only when problems have identifiable structure; for general cases, they underperform conventional optimization, and their energy predictions need independent verification.

This paper investigates whether large language models can generate parameters for quantum circuits without traditional optimization.

evaluationapplications

Ballad: Bandit-Based LLM Routing for Automated Heuristic Discovery

Nov 12, 2026

Samidha Verma, Ankit Anand, Sayan Ranu

You don't need the most expensive LLM for every task—smart routing between models using bandit algorithms can produce better solutions at lower cost by adapting which model to use based on real-time performance.

This paper presents Ballad, a bandit algorithm that dynamically selects which LLM to use at each step of automated heuristic discovery for combinatorial optimization. Rather than assuming larger models are always better, Ballad learns to orchestrate multiple LLMs into an ensemble that outperforms any single model while cutting costs by up to 66%.

agentsefficiencyreasoning

When Both Sides Adapt: The Challenges of Evaluating Interactive LLM Systems

Nov 12, 2026

Hannah Li

Evaluating LLMs in interactive settings requires measuring both model performance and how users change their behavior in response—offline benchmarks and live experiments can disagree on which model is better.

When users interact with LLMs, they adapt their prompts based on model responses, changing what the model gets evaluated on. This paper shows that offline benchmarks and live A/B tests measure different things: offline tests compare models on the same prompts, while live tests compare them on user-adapted prompts. These can rank models differently and lead to conflicting deployment decisions.

evaluationsafety

Al-Ghasali: A Computational Framework for Simulating Islamic Jurisprudential Rulings via Finite State Automata and Large Language Models

Nov 12, 2026

Elnaserledinellah Mahmoud Abdelwahab

Islamic jurisprudential logic can be formalized as deterministic finite automata with O(1) lookup time, and LLMs can safely summarize these rulings if strictly controlled by grammar constraints derived from the automaton's execution.

Al-Ghasali formalizes Islamic jurisprudential rulings as finite state automata that can be queried in constant time, then uses LLMs to generate human-readable summaries while preventing hallucination through grammar-constrained decoding. The system proves that complex juristic reasoning can be reduced to deterministic computation without losing meaning.

reasoningsafety

Scalable Conversational Assessment: Chat-Based Exams with a Two-Agent LLM Pipeline

Nov 12, 2026

Geoffrey Challen, Craig Zilles

A two-agent LLM pipeline can conduct scalable conversational assessments that mimic oral exams by separating the interviewer from the evaluator, reducing cheating risks while maintaining the ability to ask follow-up questions and assess reasoning.

This paper presents an LLM-based system that conducts interactive text-based conversations with students to assess their reasoning and argumentation skills, mimicking oral exams at scale. It uses a two-agent architecture where an interviewer asks questions while a hidden evaluator tracks progress and prevents answer leakage, tested with simulated adversarial students and deployed in a real course.

applicationsevaluationagents

Maximizing Capacity Utilization of LoRA Adapters for Mitigating the Learning-Forgetting Trade-off

Nov 12, 2026

Tomohiro Sawada, Kartik Goyal

LoRA adapters waste capacity by not fully utilizing their configured rank; adding an effective-rank regularizer during training fixes this and improves the learning-forgetting trade-off without extra computational cost.

This paper identifies why LoRA adapters underperform full fine-tuning: they don't use their full capacity. The authors show that LoRA updates have much lower effective rank than their configured rank, limiting how broadly parameter updates spread.

efficiencytrainingalignment

Cortex-FL: Agent-Mediated Collaboration for Federated Learning

Nov 12, 2026

Rui Sun, Jinfeng Peng, Zehua Cheng et al.

This system makes federated learning practical for non-experts by automating the hard parts (finding partners, negotiating terms, managing incentives) while preserving data privacy and organizational autonomy through smart contracts.

Cortex-FL is a federated learning system where AI agents help organizations collaborate on model training without sharing raw data. Users describe what model they want in plain English, and agents automatically find partners, negotiate agreements, and coordinate training—while keeping each organization in control of their own data and finances.

agentstrainingapplications

Parsed, Plausible, Wrong: Output Format Controls Silent Errors in Small-Model Semantic Parsing

Nov 12, 2026

Umar Ahmed, Maxim Dunaev, Mohammad Nour Al Awad et al.

Output format is a free design choice that dramatically impacts small model reliability: natural language encodings reduce silent semantic errors by 2-3x and improve accuracy, suggesting format selection deserves as much attention as model architecture.

Small language models fine-tuned for semantic parsing often produce grammatically correct but semantically wrong outputs that go undetected. This paper shows that the output format—how you encode the target structure—significantly affects error rates.

trainingevaluation

Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents

Nov 12, 2026

Haochen Liu, Qianhao Zhu, Zixuan Wang et al.

A decision model's ability to teach a policy through reinforcement learning is independent of its performance as an actor—poor actors can be excellent judges and teachers because they evaluate actions with full trajectory information.

This paper investigates how decision models—systems that output choices or scores—perform in three different roles: as actors (choosing actions), judges (evaluating past actions), and teachers (training policies via reinforcement learning).

agentsreasoningtraining

Symmetry in Time: A Representation Theory of Linear Recurrent Memory

Nov 12, 2026

Anif N. Shikder, Ramit Dey, Jan Minac et al.

SSMs can only track commutative groups when using diagonal real/complex updates; adding quaternion channels enables tracking of non-commutative groups like S₅ while keeping linear-time inference, and the learned weights become directly interpretable.

This paper uses representation theory to explain why standard state space models (SSMs) fail at tracking non-commutative sequences, and proposes HyperSSM, which adds quaternion-valued channels to handle complex group structures while maintaining efficient inference. The theory directly explains what SSM weights must encode, enabling interpretable learning of geometric transformations.

architecturereasoning

Cited but Unused: Parametric Provenance in Retrieval-Augmented Generation

Nov 12, 2026

Tanzeel Abbas, Tehseen Zia, David Windridge

RAG systems frequently misattribute claims to retrieved sources when they actually come from parametric memory, and current citation verification methods cannot reliably detect this—a critical issue for trustworthy AI systems.

This paper reveals that retrieval-augmented generation (RAG) systems often cite sources they didn't actually use, instead relying on knowledge baked into the model itself. By replacing facts in retrieved passages with false versions and re-querying the model, researchers found that 1.2–15.7% of cited claims come from the model's internal memory rather than the provided context.

evaluationsafetyapplications

When Expert Disagreement Hurts: Prestige and Selectivity in LLM Decision Revision

Nov 12, 2026

Yupeng Tang, Mingfeng Lin

LLMs are vulnerable to prestige bias in revision pipelines—they reverse correct answers more often than wrong ones when told disagreement comes from an 'expert,' making reversal counts a misleading safety metric.

This paper reveals a critical flaw in how LLMs revise decisions when disagreed with: they're influenced by prestige cues (like 'expert' labels) rather than argument quality, leading them to abandon correct answers.

safetyevaluationalignment

MobileProbe: Adaptive Security Evaluation of Mobile Agents via Trajectory-Aware Injection

Nov 12, 2026

Yingbin Jin, Ji'an Wang, HaoYang Chai et al.

Mobile agents are vulnerable to environmental injection attacks where attackers embed malicious instructions in UI content.

MobileProbe is a security testing framework that automatically finds vulnerabilities in mobile AI agents by injecting malicious content into phone screens. Unlike existing tests that use fixed attack payloads, MobileProbe adapts to each agent's unique behavior path, discovering where attackers can hijack the agent's actions across different apps and tasks.

safetyevaluationagents

MuSeToM: Multi-Sensory Evaluation of Belief Revision with Textual Cues Across Six Senses

Nov 12, 2026

Chunkit Chan, Kawai Chung, Sze Heng Douglas Kwok et al.

LLMs can recognize that beliefs might change but fail at the harder task of determining what the updated belief should be—they over-update on salient but insufficient evidence, exposing a gap in their theory of mind reasoning.

MuSeToM is a benchmark testing whether large language models can determine when someone should revise their beliefs based on sensory evidence and infer the updated belief state. The benchmark contains 2,415 text-based scenarios with cues from six sensory categories, revealing that models often detect belief changes but struggle to identify what the new belief should be.

evaluationreasoning

Reducing Batch Makespan for LLM Agent Workloads through Inference-Environment Coordination

Nov 12, 2026

Wei Feng, Meiling Chen, Boxiao Chen et al.

Coordinating GPU resource allocation, cache-aware scheduling, and environment execution can significantly speed up batch processing of agent workloads without sacrificing accuracy.

This paper optimizes batch execution of LLM agent tasks by coordinating inference and environment interaction. It introduces resource allocation strategies for hybrid LLMs, trajectory-aware routing for cache reuse, and Chain-Advancing Action Scheduling to handle environment bottlenecks—achieving 10-65% makespan reductions on real benchmarks.

efficiencyagentstraining

Asymmetric Multimodal Learning with Decomposed JEPAs

Nov 12, 2026

Yusuf Shihata

For multimodal AI systems, alignment-only training catastrophically fails on compositional reasoning when modalities carry different types of information—you need to explicitly preserve modality-specific structure alongside alignment.

This paper shows that standard cross-modal alignment alone loses important information when modalities are asymmetric (like text queries and images). It introduces Decomposed JEPA, which splits learned representations into a shared aligned part and private modality-specific parts, recovering information that alignment discards and improving performance on reasoning tasks.

multimodalarchitecturetraining

When Chekhov's Gun Fires Anyway: Over-Realization in Text-to-Image Models

Nov 12, 2026

Jiahao Huang, Kon Woo Kim, Song-Duo Ma et al.

Text-to-image generators fail to respect linguistic context (negations, beliefs, figurative language, hidden viewpoints) and generate unwanted objects anyway; existing metrics don't catch this, making it a blind spot in current evaluation.

Text-to-image models often generate objects mentioned in prompts even when the prompt doesn't ask for them—like showing a gun in a negation or imagination. This paper introduces OverReal, a benchmark measuring this 'over-realization' failure across four linguistic contexts, revealing all major models struggle with it and that standard metrics actually reward the problem.

evaluationmultimodal

Safety as a Budget: Calibrating the Control Channel of Constrained GRPO for Vision-Language Models

Nov 12, 2026

Bo Han

You can directly control VLM safety by setting explicit budgets on harmful assistance rates and using a two-channel reward design that preserves the safety multiplier signal through training.

This paper addresses how to directly control safety in vision-language models using reinforcement learning. The authors propose a two-channel constrained GRPO method that treats safety as explicit budgets (acceptable rates of harmful outputs and over-refusal) enforced through Lagrange multipliers.

safetyalignmentmultimodal

Folio: Recoverable Multi-Resolution Context Folding for Long-Horizon Language Agents

Nov 12, 2026

Yubo Ruan, Tao Peng, Jiao Zhang et al.

By recording context at multiple levels and folding programmatically rather than summarizing with the model, agents can handle longer histories more efficiently—solving 66/75 tasks vs 54 with model summarization, in half the time and 2.4x lower cost.

Folio is a context manager for long-horizon language agents that replaces model-based summarization with a multi-level recording system.

agentsefficiencyreasoning

Unibuc - NLP at "Voight-Kampff" Generative AI Detection PAN 2025

Nov 12, 2026

Teodor Marchitan, Claudiu Creanga, Liviu P. Dinu

Ensemble methods using embeddings from LLMs with classical ML models can match or exceed fine-tuned LLM performance for AI-generated text detection, suggesting embeddings alone capture sufficient signal for this task.

This paper presents methods for detecting AI-generated text and classifying human-AI collaborative writing. The team experimented with LLM embeddings combined with classical machine learning models (achieving 99.4% F1) and transformer-based feature extraction for two related detection tasks at PAN 2025.

evaluationapplications

AutoScaffold: AI-Guided Scaffolding for Reinforcement Learning of Language Models

Nov 10, 2026

Zijian Zhang, Rizhen Hu, Jiangweizhi Peng et al.

Automatically generated, adaptive training scaffolds can significantly improve RL-trained language models by turning failure information into targeted guidance, with gains persisting even after scaffolds are removed at evaluation.

AutoScaffold is an AI system that automatically creates and adapts training guidance (scaffolds) for language models learning through reinforcement learning. A frozen teacher analyzes the student model's failures during training, diagnoses problems, and generates helpful strategies or hints that are removed at test time.

trainingreasoningagents

Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations

Nov 10, 2026

Ziang Liu, James J. Kim, Yijia Dai et al.

LLM agents can resolve scientific questions more effectively by scoring experiments based on how evidence redistributes belief across competing explanations, rather than just testing whether a single hypothesis is true or false.

This paper introduces Contrastive Discovery, a method for LLM agents to conduct scientific research more effectively by evaluating multiple competing explanations simultaneously rather than testing single hypotheses.

agentsreasoningevaluation

Pyrite: Building and Benchmarking Protein-Ligand Pose Ranking Agents

Nov 10, 2026

Megha Srivastava, Michael H. Lim, Allison M. Keys et al.

LLMs can discover useful features from molecular data better than direct reasoning, and this feature-discovery approach beats expert chemists at ranking binding poses—a critical step in drug design.

Pyrite is a benchmark for ranking protein-ligand binding poses in drug discovery, where LLM-based agents outperform human experts. The paper introduces two AI approaches: one that reasons about poses directly, and another that generates code to discover predictive features, achieving up to 74% accuracy on 1,500 pose pairs.

applicationsagentsreasoning

Continual-ARC: Measuring Skill Acquisition over a Working Lifetime

Nov 10, 2026

Daniel Lenton

Current agent harness methods for continual learning underperform simple memory-based baselines on repeated tasks, but weight-based learning shows potential for generalizing to new domains—suggesting future work should focus on training models to better use external tools and memory systems.

This paper introduces Continual-ARC, a benchmark for measuring how AI agents learn over time by solving tasks from the ARC-AGI dataset. Tasks repeat with new instances and new tasks arrive continuously, mimicking real-world learning.

trainingevaluationagents

Emergent Biological Capabilities in a Foundation Model for Molecular Interactions

Nov 10, 2026

Adi Mashiach

Foundation models can develop unexpected biological reasoning abilities through scale alone, and these emergent capabilities don't follow smooth scaling laws—they appear suddenly at larger model sizes, suggesting qualitative jumps in what AI can do with molecular data.

Bonbon is a foundation model trained on 3.2 trillion tokens of protein-ligand sequences that unexpectedly develops three distinct capabilities for predicting molecular interactions—mechanism of action, binding site location, and bond type—without explicit training for these tasks.

scalingmultimodalapplications

Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents

Nov 10, 2026

Howard Zhang, Chuck Arvin, Logan Brown et al.

When evaluating LLM agents in production, combine trace-based evaluation for functional correctness with adversarial red-teaming for security—they catch different failure types that neither method finds alone.

This paper compares three evaluation frameworks for LLM-based analytics agents in enterprise settings, testing their ability to detect failures across complex workflows.

evaluationagentssafety

ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

Nov 10, 2026

Kaiyuan Hou, Yang Ping Kuo, Indranil Bhattacharya et al.

You can replace expensive LLM calls in repetitive business processes with rule-based code by learning decision logic from agent execution traces—achieving near-agent performance at a fraction of the latency and cost.

ReTrace converts LLM agent workflows into fast, cost-efficient code-based processes by extracting decision rules from agent reasoning logs. It analyzes why agents took actions, distills these explanations into compact rule documents, and generates executable workflows that run 130x faster at 24% lower cost while maintaining 93.8% success on production tasks.

agentsefficiencyapplications

Re-Search: Dissecting LLM Ideation Through a Two-Player Questioning Game

Nov 10, 2026

Muhan Gao, Hangxiao Zhu, Xinqi Su et al.

LLMs are better at judging research ideas than generating them; improving ideation systems may require external idea sources rather than just better individual model generation.

This paper introduces Re-Search, a benchmark that evaluates how LLMs explore research ideas through a Twenty Questions-style game. Given only a research problem, models must rediscover a paper's core idea by asking yes-or-no questions and receiving binary feedback.

evaluationreasoningagents

Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation

Nov 10, 2026

Evelyn Y. Garland, Carola F. Berger

Using LLMs as judges with careful prompt engineering and ROC-guided model selection can deliver competitive translation quality evaluation at a fraction of typical inference costs.

Pterodactyl is a cost-efficient system for evaluating machine translation quality at the segment level. It uses an LLM-as-a-judge approach with optimized prompting to predict quality scores and identify error-free translations, designed for practical deployment in translation workflows.

evaluationapplications

C$^2$-Routing: Complementary Cropping and Compression for Efficient Vision-Language Inference

Nov 10, 2026

Guorui Lu, Qinyu Chen

Cropping and compression are complementary strategies for reducing VLM inference cost—use cropping for detail-focused questions and compression for context-heavy ones, with a learned safety mechanism to protect accuracy.

This paper proposes C²-Routing, a method that adaptively chooses between cropping (for local details) and compression (for context) to reduce computational costs in vision-language models for VQA tasks. It includes a safety gate to prevent accuracy loss and achieves 36.53% FLOP reduction with minimal performance drop.

efficiencymultimodalapplications
evaluationagentsreasoning

Saidzoda-CA-EmbeddingGemma-300M: One Small Embedder for Tajik, Kazakh, Uzbek and Kyrgyz

Nov 8, 2026

Tohir Saidzoda, Nekruz Maxudov, Bedil Karimov et al.

A single small embedding model can serve multiple low-resource languages effectively through targeted fine-tuning with synthetic data, but scaling up to larger multilingual models remains necessary for competitive performance on these languages.

Researchers fine-tuned a small 300M embedding model (EmbeddingGemma) to work across four Central Asian languages—Tajik, Kazakh, Uzbek, and Kyrgyz—using synthetic question-answer pairs generated by a language model. The fine-tuned model significantly improved retrieval performance (14-26 percentage points) on a multilingual benchmark, though it still lags behind larger 560M multilingual models.

multimodaltrainingefficiency

GOPR-CAD: Graph-of-Operations Progressive Reasoning for CAD Generation

Nov 8, 2026

Yitian Pang, Yifan Li, Xiaowei Yue et al.

Decomposing CAD generation into discrete operations that an LLM selects sequentially, rather than generating full code at once, dramatically improves structural correctness (82.7% success rate) and works with any language model without retraining.

This paper presents GOPR-CAD, a system that generates CAD models from text by having an AI agent progressively build a graph of operations rather than directly writing code.

agentsreasoningapplications

RealEmbedBench: Benchmarking LLMs on Real-World Application-Layer Embedded Software Tasks

Nov 8, 2026

Yujun Huang, Yuwei Zhang, Yi Zhou et al.

LLMs show uneven performance on embedded software tasks: they need local code context to generate code effectively, can model state machines but fail at implementing them, and struggle with certain OS-to-OS translations, suggesting developers should choose models carefully and provide surrounding...

RealEmbedBench is a benchmark with 5,142 real-world embedded software tasks testing LLMs on code generation, state machine modeling, and cross-OS translation.

evaluationapplications

Semantically Aligned KV Cache Compression for Efficient Agentic Autoregressive Video Generation

Nov 8, 2026

Weizhong Huang, Huaijia Kou, Tianyu Xie et al.

By aligning KV cache compression with semantic planning constraints, you can reduce memory usage by 3.35x and speed up video generation by 1.22x without retraining, making agentic video generation more practical for resource-constrained settings.

This paper presents SemanticKV, a method to compress the key-value cache in video generation models by using semantic constraints from a planner to decide which cached information to keep.

efficiencymultimodalagents

How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate?

Nov 8, 2026

Cong Yu, Ziting Wang, Songlin Jiang et al.

On-policy distillation tolerates significant training-inference mismatch from quantization and asynchronous rollouts without quality loss, enabling 1.6× faster training with FP8 precision while maintaining performance.

This paper studies how much training-inference mismatch on-policy distillation (OPD) can tolerate when using quantized inference and asynchronous rollouts to reduce training costs.

trainingefficiency

SWHForest: A Structural Curation and Search Layer for Large-Scale Code Corpora

Nov 8, 2026

Federico Pennino, Andrea Gurioli, Maurizio Gabbrielli et al.

For code model pre-training, you can now query structural properties (AST patterns, definitions, etc.) across massive corpora in seconds without downloading everything—enabling faster, more targeted dataset curation.

SWHForest is a framework that creates a searchable structural index of code files without storing source code, letting researchers efficiently filter and curate large code corpora before downloading. Instead of downloading millions of files to find what they need, users can query the index to identify matching files first, reducing downloads by 46-72%.

datatrainingapplications

Flex-DDCM: Zero-Shot Task-Oriented Image Compression via Diffusion Trajectory Guidance

Nov 8, 2026

Yixin Gao, Runsen Feng, Xin Li et al.

You can compress images for specific AI tasks (like object detection) without retraining by steering a pretrained diffusion model's denoising process with task guidance signals—enabling one codec to serve multiple purposes.

This paper presents Flex-DDCM, a zero-shot image compression method that uses diffusion models to compress images while optimizing for specific downstream tasks. By guiding the diffusion denoising process with task-specific signals, it achieves flexible trade-offs between image quality and task performance without requiring task-specific training.

efficiencymultimodalapplications

On Agentic Manipulation Policies

Nov 6, 2026

Chen Chen, Omid Bagherieh, Naveen Nikamanth Appiah Balaji et al.

Generalist AI agents controlling robots directly outperform specialist manipulation policies by 15-20x in failure rates, and can learn from experience with memory—suggesting agentic approaches are more robust and general than task-specific models.

This paper shows that generalist AI models can control robot manipulators more reliably than specialist policies by using agentic manipulation policies (AMPs)—where an AI agent directly commands the robot and adapts actions in real-time. AMP1, their reference system, achieves 85.6% zero-shot success on RoboLab-120 (vs.

agentsapplicationsreasoning

CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse

Nov 6, 2026

Peter Belcak, Greg Heinrich, Saurav Muralidharan et al.

You can extract and cache the reasoning logic from LLM problem-solving into reusable CPU programs, eliminating redundant computation and dramatically reducing inference costs while maintaining performance.

This paper introduces agentic reasoning caching (ARC), a method that extracts reasoning logic from LLM traces and converts it into efficient, CPU-executable programs. Instead of re-solving problems from scratch, ARCs apply learned solution patterns to new instances, achieving comparable performance to frontier LLMs while being 16-291x cheaper and fully explainable.

efficiencyreasoningagents

On the Reliability of Majority-Vote Pseudo-Labels in Test-Time Reinforcement Learning

Nov 6, 2026

Haoyu Wang, Ru Wang, Yuanyuan Wang et al.

When adapting language models at test time using self-generated labels, you should weight updates based on how reliable the voting signal is for each prompt—this prevents the model from learning from noisy pseudo-labels.

This paper addresses a key problem in test-time reinforcement learning: how reliable are the self-generated labels used to adapt language models? The authors analyze majority-vote pseudo-labels, identify sources of error, and propose PC-Dr.DPO, a method that makes the model more cautious when updating from unreliable prompts. They validate their approach across math and reasoning tasks.

trainingalignmentefficiency

CodeQuant2: Enhanced Outlier Mitigation and Adaptive Clustering for Low-Precision LRMs

Nov 6, 2026

Xingyu Liu, Xiangyang Yin, Tianhua Xia et al.

Reasoning models need special quantization handling because they show larger activation fluctuations early in generation—CodeQuant2 captures this with adaptive clustering and better calibration, achieving 2.85× speedup with minimal accuracy loss.

CodeQuant2 is a quantization technique that compresses large reasoning models to low precision while maintaining accuracy. It addresses unique challenges in reasoning models by detecting and handling unusual activation patterns in early decoding steps, using clustering to represent weights efficiently, and adapting compression levels per layer.

efficiencytraining

GRAC: Graph-Based Retrieval-Augmented Captioning for Surgical Scene Description

Nov 6, 2026

Rochak Dhakal, Chen Zhao, Soup Cobb et al.

Combining structured scene graphs with retrieval-augmented generation substantially improves surgical scene captioning accuracy and factual correctness, suggesting that domain-specific structured representations can enhance LLM-based medical documentation.

GRAC is a system that automatically generates descriptions of surgical scenes by combining graph representations of surgical elements (instruments, actions, anatomy) with retrieval-augmented generation. It retrieves similar past surgical scenes and uses them to guide caption generation, achieving significantly better descriptions than existing methods on surgical video benchmarks.

multimodalapplications

Computer-Use Agents Are Embodied Generalists

Nov 6, 2026

Pranjal Aggarwal, Sean Welleck

General-purpose computer-use agents can solve diverse embodied tasks without specialization, pointing toward a unified approach to embodied AI rather than task-specific models.

This paper shows that computer-use agents—AI systems trained to interact with software via screenshots and mouse/keyboard actions—can perform physical embodied tasks by rendering the environment on a screen.

agentsapplicationsmultimodal