Paper Detail

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

Zilin Xiao, Qi Ma, Chun-cheng Jason Chen, Xintao Chen, Avinash Atreya, Hanjie Chen, Vicente Ordonez

arxiv Score 14.3

Published 2026-06-11 · First seen 2026-06-13

General AI

Abstract

Retrieval-augmented generation (RAG) has become a standard mechanism for grounding language models in external knowledge, yet conventional retrieval based on lexical or semantic similarity is poorly suited for complex reasoning tasks: a semantically similar problem may demand an entirely different solution strategy, while a superficially different problem may share the same underlying reasoning pattern. We propose Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT), a post-training framework that teaches language models to reason by analogy. RA-RFT uses gold-relevance distillation to train a retriever that ranks contexts by expected reasoning benefit rather than semantic overlap, and then fine-tunes the policy model via reinforcement fine-tuning methods with retrieved analogous demonstrations, so the model learns to leverage reasoning traces under verifiable outcome rewards. We further analyze the diversity of retrieved contexts and find that reasoning-aware retrieval surfaces complementary solution strategies that provide distinct reasoning scaffolds for individual problems. Across challenging mathematical reasoning benchmarks, RA-RFT consistently outperforms standard reinforcement fine-tuning methods. For example, it improves AIME 2025 average@32 accuracy by 7.1 and 2.8 points over GRPO for Qwen3-1.7B and Qwen3-4B respectively -- suggesting that reasoning-aware retrieval is a complementary axis of improvement and orthogonal to advances in reward design or training curricula.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{xiao2026learning,
  title = {Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning},
  author = {Zilin Xiao and Qi Ma and Chun-cheng Jason Chen and Xintao Chen and Avinash Atreya and Hanjie Chen and Vicente Ordonez},
  year = {2026},
  abstract = {Retrieval-augmented generation (RAG) has become a standard mechanism for grounding language models in external knowledge, yet conventional retrieval based on lexical or semantic similarity is poorly suited for complex reasoning tasks: a semantically similar problem may demand an entirely different solution strategy, while a superficially different problem may share the same underlying reasoning pattern. We propose Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT), a post-training framework },
  url = {https://arxiv.org/abs/2606.13680},
  keywords = {cs.CL, cs.AI},
  eprint = {2606.13680},
  archiveprefix = {arXiv},
}

Metadata

{}