Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning

Zilin Xiao, Qi Ma, Chun-cheng Jason Chen, Xintao Chen, Avinash Atreya et al.|June 11, 2026arXiv

Key Takeaway

Retrieving problems with similar reasoning strategies—not just semantic similarity—helps language models solve complex reasoning tasks better, and this works alongside other training improvements.

Summary

This paper teaches language models to solve complex problems by learning from analogous examples rather than just semantically similar ones. It introduces a system that retrieves problems with similar reasoning patterns (not just similar wording) and uses reinforcement learning to help models learn from these examples, improving performance on math reasoning tasks.

reasoning training

Key Terms

retrieval-augmented-generation reasoning-aware-retrieval gold-relevance-distillation reinforcement-fine-tuning reasoning-trace