@inproceedings{zhuang-etal-2026-workforceagent,
    title = "{W}ork{F}orce{A}gent-R1: Incentivizing Reasoning Capability in {LLM}-based Web Agents via Reinforcement Learning",
    author = "Zhuang, Yuchen  and
      Jin, Di  and
      Chen, Jiaao  and
      Shi, Wenqi  and
      Wang, Hanrui  and
      Zhang, Chao",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.3/",
    pages = "34--49",
    ISBN = "979-8-89176-386-9",
    abstract = "Large language model (LLM)-empowered web agents enable automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on supervised fine-tuning (SFT) often struggle with generalization and robustness due to insufficient reasoning capabilities when handling the inherently dynamic nature of web interactions. In this study, we introduce WorkForceAgent-R1, an LLM-based web agent trained using a rule-based R1-style reinforcement learning framework explicitly designed to enhance single-step reasoning and planning for business-oriented web navigation tasks. We employ a structured reward function that evaluates both adherence to output formats and correctness of actions, enabling WorkForceAgent-R1 to implicitly learn robust intermediate reasoning without explicit annotations or extensive expert demonstrations. Extensive experiments on the WorkArena benchmark demonstrate that WorkForceAgent-R1 substantially outperforms SFT baselines by 10.26{--}16.59{\%}, achieving competitive performance relative to proprietary LLM-based agents (GPT-4o) in workplace-oriented web navigation tasks."
}