# Learning from Peers in Reasoning Models

arXiv: https://arxiv.org/abs/2505.07787 · HTML: https://mlsanity.com/paper/2505.07787/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 12 May 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 26 of 26)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild](https://mlsanity.com/paper/2503.18892/) (2025)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling](https://mlsanity.com/paper/2406.00832/) (2024)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (2024)
- [Fast Best-of-N Decoding via Speculative Rejection](https://mlsanity.com/paper/2410.20290/) (2024)
- [DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning](https://mlsanity.com/paper/2504.07128/) (2025)
- [An Empirical Study on Eliciting and Improving R1-like Reasoning Models](https://mlsanity.com/paper/2503.04548/) (2025)
- [BOND: Aligning LLMs with Best-of-N Distillation](https://mlsanity.com/paper/2407.14622/) (2024)
- [MALT: Improving Reasoning with Multi-Agent LLM Training](https://mlsanity.com/paper/2412.01928/) (2024)
- [Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration](https://mlsanity.com/paper/2310.00280/) (2023)
- [Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?](https://mlsanity.com/paper/2502.12215/) (2025)
- [Variational Best-of-N Alignment](https://mlsanity.com/paper/2407.06057/) (2024)
- [Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective](https://mlsanity.com/paper/2412.14135/) (2024)
- [START: Self-taught Reasoner with Tools](https://mlsanity.com/paper/2503.04625/) (2025)
- [CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving](https://mlsanity.com/paper/2404.17729/) (2024)
- [The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models](https://mlsanity.com/paper/2503.02875/) (2025)
- [SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents](https://mlsanity.com/paper/2411.03284/) (2024)
- [When is the consistent prediction likely to be a correct prediction?](https://mlsanity.com/paper/2407.05778/) (2024)

## Built on by (most cited first, 16 of 16)

- [Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models](https://mlsanity.com/paper/2508.10751/) (2025)
- [A Survey on Parallel Reasoning](https://mlsanity.com/paper/2510.12164/) (2025)
- [Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework](https://mlsanity.com/paper/2507.06829/) (2025)
- [Monitor-Generate-Verify (MGV): Formalising Metacognitive Theory for Language Model Reasoning](https://mlsanity.com/paper/2511.04341/) (2025)
- [Before you <think>, monitor: Implementing Flavell's metacognitive framework in LLMs](https://mlsanity.com/paper/2510.16374/) (2025)
- [Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework](https://mlsanity.com/paper/2509.05007/) (2025)
- [Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling](https://mlsanity.com/paper/2605.27030/) (2026)
- [A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning](https://mlsanity.com/paper/2509.22044/) (2025)
- [Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart](https://mlsanity.com/paper/2601.11940/) (2026)
- [Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning](https://mlsanity.com/paper/2602.00759/) (2026)
- [Peer-Predictive Self-Training for Language Model Reasoning](https://mlsanity.com/paper/2604.13356/) (2026)
- [TMAS: Scaling Test-Time Compute via Multi-Agent Synergy](https://mlsanity.com/paper/2605.10344/) (2026)
- [EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance](https://mlsanity.com/paper/2509.23730/) (2025)
- [OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration](https://mlsanity.com/paper/2602.08344/) (2026)
- [Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning](https://mlsanity.com/paper/2604.16029/) (2026)
- [COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference](https://mlsanity.com/paper/2609.26913/) (2026)

## Abstract (arXiv)

Large Reasoning Models (LRMs) have the ability to self-correct even when they make mistakes in their reasoning paths. However, our study reveals that when the reasoning process starts with a short but poor beginning, it becomes difficult for the model to recover. We refer to this phenomenon as the "Prefix Dominance Trap". Inspired by psychological findings that peer interaction can promote self-correction without negatively impacting already accurate individuals, we propose **Learning from Peers** (LeaP) to address this phenomenon. Specifically, every tokens, each reasoning path summarizes its intermediate reasoning and shares it with others through a routing mechanism, enabling paths to incorporate peer insights during inference. However, we observe that smaller models sometimes fail to follow summarization and reflection instructions effectively. To address this, we fine-tune them into our **LeaP-T** model series. Experiments on AIME 2024, AIME 2025, AIMO 2025, and GPQA Diamond show that LeaP provides substantial improvements. For instance, QwQ-32B with LeaP achieves nearly 5 absolute points higher than the baseline on average, and surpasses DeepSeek-R1-671B on three math benchmarks with an average gain of 3.3 points. Notably, our fine-tuned LeaP-T-7B matches the performance of DeepSeek-R1-Distill-Qwen-14B on AIME 2024. In-depth analysis reveals LeaP's robust error correction by timely peer insights, showing strong error tolerance and handling varied task difficulty. LeaP marks a milestone by enabling LRMs to collaborate during reasoning. Our code, datasets, and models are available at https://learning-from-peers.github.io/ .