@inproceedings{guan-etal-2026-evidence,
    title = "Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning",
    author = "Guan, Xin  and
      Li, Zijian  and
      Huang, Shen  and
      Xie, Pengjun  and
      Zhou, Jingren  and
      Cao, Jiuxin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1404/",
    pages = "30440--30454",
    ISBN = "979-8-89176-390-6",
    abstract = "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."
}