paper-with-me

홈 › Papers

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

2026-01-15 · Xin Guan, Zijian Li, Shen Huang, Pengjun Xie, Jingren Zhou, Jiuxin Cao 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.

📄 PDF Abstract BibTeX arXiv:2601.10306

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

2026-05-11 · Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang, Jun Yan 외 arxiv

Training deep research agents, namely systems that plan, search, evaluate evidence, and synthesize long-form reports, pushes reinforcement learning beyond the regime of verifiable rewards. Their outputs lack ground-truth…

Reinforcement Learning

SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning

2026-07-29 · Jianze Wang, Kunwang Zheng, Ying Liu, Yu Cao 외 arxiv

Test-time reinforcement learning (TTRL) enables language models to self-evolve at inference time without labeled feedback. Existing methods rely on answer voting and therefore do not extend naturally to open-ended genera…

Reinforcement Learning

Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards

2026-07-24 · Ruoxi Cheng, Haoxuan Ma, Hongyi Zhang, Junming Zhang 외 arxiv

Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Existing external rewards provide either sparse outcome supervision or richer feed…

OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning

2025-10-28 · Ziyou Hu, Zhengliang Shi, Minghang Zhu, Haitao Li 외 arxiv

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive …

Reinforcement Learning

Evo-RAD: Navigating Rare Retinal Disease Diagnosis via Self-Evolving Agentic Retrieval

2026-06-22 · Wangding Xia, Ye Du, Jiashi Lin, Meng Wang 외 arxiv

Large-scale pretrained foundation models have revolutionized general medical screening, but often falter on rare diseases because such conditions are underrepresented in real-world clinical datasets. While retrieval-augm…

parameter-efficient fine-tuning