@inproceedings{yu-etal-2026-webanchor,
    title = "{W}eb{A}nchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning",
    author = "Yu, Xinmiao  and
      Zhang, Liwen  and
      Feng, Xiaocheng  and
      Xie, Pengjun  and
      Zhou, Jingren  and
      Qin, Bing  and
      Jiang, Yong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.2058/",
    pages = "41368--41380",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Model(LLM)-based agents have shown strong capabilities in web information seeking, with reinforcement learning (RL) becoming a key optimization paradigm. However, planning remains a bottleneck, as existing methods struggle with long-horizon strategies. Our analysis reveals a critical phenomenon{---}plan anchor{---}where the first reasoning step disproportionately impacts downstream behavior in long-horizon web reasoning tasks. Current RL algorithms, fail to account for this by uniformly distributing rewards across the trajectory.To address this, we propose Anchor-GRPO, a two-stage RL framework that decouples planning and execution. In Stage 1, the agent optimizes its first-step planning using fine-grained rubrics derived from self-play experiences and human calibration. In Stage 2, execution is aligned with the initial plan through sparse rewards, ensuring stable and efficient tool usage. We evaluate Anchor-GRPO on four benchmarks: BrowseComp, BrowseComp-Zh, GAIA, and XBench-DeepSearch. Across models from 3B to 30B, Anchor-GRPO outperforms baseline GRPO and First-step GRPO, improving task success and tool efficiency. Notably, WebAnchor-30B achieves 46.0{\%} pass@1 on BrowseComp and 76.4{\%} on GAIA. Anchor-GRPO also demonstrates strong scalability, getting higher accuracy as model size and context length increase."
}