# Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision

arXiv: https://arxiv.org/abs/2502.20790 · HTML: https://mlsanity.com/paper/2502.20790/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 33 of its 50 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (2024)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models](https://mlsanity.com/paper/2312.06585/) (2023)
- [ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search](https://mlsanity.com/paper/2406.03816/) (2024)
- [LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens](https://mlsanity.com/paper/2402.13753/) (2024)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024)
- [Data Engineering for Scaling Language Models to 128K Context](https://mlsanity.com/paper/2402.10171/) (2024)
- [How to Train Long-Context Language Models (Effectively)](https://mlsanity.com/paper/2410.02660/) (2024)
- [Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango](https://mlsanity.com/paper/2209.07686/) (2022)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training](https://mlsanity.com/paper/2309.10400/) (2023)
- [Why Does the Effective Context Length of LLMs Fall Short?](https://mlsanity.com/paper/2410.18745/) (2024)
- [Long Code Arena: a Set of Benchmarks for Long-Context Code Models](https://mlsanity.com/paper/2406.11612/) (2024)
- [LongEmbed: Extending Embedding Models for Long Context Retrieval](https://mlsanity.com/paper/2404.12096/) (2024)

## Built on by (most cited first, 21 of 21)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization](https://mlsanity.com/paper/2505.15107/) (2025)
- [PonderLM: Pretraining Language Models to Ponder in Continuous Space](https://mlsanity.com/paper/2505.20674/) (2025)
- [Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training](https://mlsanity.com/paper/2509.03403/) (2025)
- [ReCode: Reinforcing Code Generation with Reasoning-Process Rewards](https://mlsanity.com/paper/2508.05170/) (2025)
- [ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models](https://mlsanity.com/paper/2510.01290/) (2025)
- [JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting](https://mlsanity.com/paper/2606.18394/) (2026)
- [LastingBench: Defend Benchmarks Against Knowledge Leakage](https://mlsanity.com/paper/2506.21614/) (2025)
- [TreeDiff: AST-Guided Code Generation with Diffusion LLMs](https://mlsanity.com/paper/2508.01473/) (2025)
- [Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation](https://mlsanity.com/paper/2511.02303/) (2025)
- [SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization](https://mlsanity.com/paper/2505.11166/) (2025)
- [Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization](https://mlsanity.com/paper/2604.14267/) (2026)
- [Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning](https://mlsanity.com/paper/2601.10306/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Read More, Think More: Revisiting Observation Reduction for Web Agents](https://mlsanity.com/paper/2604.01535/) (2026)
- [Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization](https://mlsanity.com/paper/2508.13993/) (2025)
- [Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems](https://mlsanity.com/paper/2510.24476/) (2025)
- [Structured Reasoning with Tree-of-Thoughts for Bengali Math Word Problems](https://mlsanity.com/paper/2512.05580/) (2025)
- [Probing How Scalable Table Data Enhances General Long-Context Reasoning](https://mlsanity.com/paper/2603.21719/) (2026)
- [Can LLM Teams Play What? Where? When?](https://mlsanity.com/paper/2605.30459/) (2026)
- [Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs](https://mlsanity.com/paper/2606.06203/) (2026)

## Abstract (arXiv)

Recent advances in Large Language Models (LLMs) have highlighted the challenge of handling long-context tasks, where models need to reason over extensive input contexts to aggregate target information. While Chain-of-Thought (CoT) prompting has shown promise for multi-step reasoning, its effectiveness for long-context scenarios remains underexplored. Through systematic investigation across diverse tasks, we demonstrate that CoT's benefits generalize across most long-context scenarios and amplify with increasing context length. Motivated by this critical observation, we propose LongRePS, a process-supervised framework that teaches models to generate high-quality reasoning paths for enhanced long-context performance. Our framework incorporates a self-sampling mechanism to bootstrap reasoning paths and a novel quality assessment protocol specifically designed for long-context scenarios. Experimental results on various long-context benchmarks demonstrate the effectiveness of our approach, achieving significant improvements over outcome supervision baselines on both in-domain tasks (+13.6/+3.8 points for LLaMA/Qwen on MuSiQue) and cross-domain generalization (+9.3/+8.1 points on average across diverse QA tasks). Our code, data and trained models are made public to facilitate future research.