CompressionBench: How can your coding agents compress LLMs?

Xinrui Zhong, Zhifeng Li, Zhiming Wang, Yongqi Liu, Shanglin Yang et al.|November 4, 2026arXiv

Key Takeaway

Coding agents can autonomously compress LLMs with reasonable success, but their performance depends heavily on how they design experiments, interpret feedback, and validate results—not just on compression algorithm choice.

Summary

This paper studies whether AI coding agents can autonomously compress large language models to fit storage constraints while maintaining performance. Agents receive a source model, storage limit, and time budget, then design compression algorithms and write inference code.

efficiency agents evaluation

Key Terms

model-compression perplexity agentic-language-model recursive-self-improvement verification