# Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning

arXiv: https://arxiv.org/abs/2601.10306 · HTML: https://mlsanity.com/paper/2601.10306/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 19 of 19)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models](https://mlsanity.com/paper/2501.09686/) (2025)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Process Reward Models That Think](https://mlsanity.com/paper/2504.16828/) (2025)
- [DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning](https://mlsanity.com/paper/2511.22570/) (2025)
- [SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models](https://mlsanity.com/paper/2506.01062/) (2025)
- [QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning](https://mlsanity.com/paper/2505.17667/) (2025)
- [ReCode: Reinforcing Code Generation with Reasoning-Process Rewards](https://mlsanity.com/paper/2508.05170/) (2025)
- [Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision](https://mlsanity.com/paper/2502.20790/) (2025)
- [Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning](https://mlsanity.com/paper/2509.06436/) (2025)

## Built on by (most cited first, 7 of 7)

- [EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation](https://mlsanity.com/paper/2605.29847/) (2026)
- [LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards](https://mlsanity.com/paper/2602.05758/) (2026)
- [LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards](https://mlsanity.com/paper/2605.31584/) (2026)
- [InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain](https://mlsanity.com/paper/2606.03329/) (2026)
- [Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning](https://mlsanity.com/paper/2606.18831/) (2026)
- [Evidence-State Rewards for Long-Context Reasoning](https://mlsanity.com/paper/2607.02073/) (2026)
- [A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering](https://mlsanity.com/paper/2608.26949/) (2026)

## Abstract (arXiv)

While Reinforcement Learning (RL) has advanced LLM reasoning, applying it to long-context scenarios is hindered by sparsity of outcome rewards. This limitation fails to penalize ungrounded "lucky guesses," leaving the critical process of needle-in-a-haystack evidence retrieval largely unsupervised. To address this, we propose EAPO (Evidence-Augmented Policy Optimization). We first establish the Evidence-Augmented Reasoning paradigm, validating via Tree-Structured Evidence Sampling that precise evidence extraction is the decisive bottleneck for long-context reasoning. Guided by this insight, EAPO introduces a specialized RL algorithm where a reward model computes a Group-Relative Evidence Reward, providing dense process supervision to explicitly improve evidence quality. To sustain accurate supervision throughout training, we further incorporate an Adaptive Reward-Policy Co-Evolution mechanism. This mechanism iteratively refines the reward model using outcome-consistent rollouts, sharpening its discriminative capability to ensure precise process guidance. Comprehensive evaluations across eight benchmarks demonstrate that EAPO significantly enhances long-context reasoning performance compared to SOTA baselines.