# Evidence-State Rewards for Long-Context Reasoning

arXiv: https://arxiv.org/abs/2607.02073 · HTML: https://mlsanity.com/paper/2607.02073/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [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)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [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)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (2024)
- [LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens](https://mlsanity.com/paper/2402.13753/) (2024)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [Process Reward Models That Think](https://mlsanity.com/paper/2504.16828/) (2025)
- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion](https://mlsanity.com/paper/2501.15089/) (2025)
- [QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning](https://mlsanity.com/paper/2505.17667/) (2025)
- [LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering](https://mlsanity.com/paper/2410.18050/) (2024)
- [LongReward: Improving Long-context Large Language Models with AI Feedback](https://mlsanity.com/paper/2410.21252/) (2024)
- [LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts](https://mlsanity.com/paper/2510.19363/) (2025)
- [LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards](https://mlsanity.com/paper/2603.02146/) (2026)
- [LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards](https://mlsanity.com/paper/2602.05758/) (2026)
- [Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning](https://mlsanity.com/paper/2601.10306/) (2026)

## Built on by (most cited first, 1 of 1)

- [LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management](https://mlsanity.com/paper/2610.13075/) (2026)

## Abstract (arXiv)

Long-context reasoning requires models to locate, revise, and synthesize evidence distributed across lengthy inputs. Existing long-context RL methods usually reward final answers or static evidence extraction, offering little feedback on how intermediate actions change the model's evidence state. We propose Maven, a reinforcement learning framework with an editable evidence memory. Maven defines an answer-conditioned evidence-state value and rewards action-level state transitions: add actions are credited by marginal gain and hindsight contribution, link actions by evidence synergy, and drop actions by improved answer support after removing misleading evidence. These rewards are assigned to the corresponding action spans in GRPO. Across Llama and Qwen models on LongBench v2, LongReason, and RULER, Maven outperforms outcome-only RL and evidence-identification baselines, producing more sufficient evidence sets and lower distractor retention. Our results show that long-context RL benefits from optimizing stateful evidence navigation rather than one-shot evidence extraction.