@inproceedings{rozanov-rei-2025-stateact,
    title = "{S}tate{A}ct: Enhancing {LLM} Base Agents via Self-prompting and State-tracking",
    author = "Rozanov, Nikolai  and
      Rei, Marek",
    editor = "Kamalloo, Ehsan  and
      Gontier, Nicolas  and
      Lu, Xing Han  and
      Dziri, Nouha  and
      Murty, Shikhar  and
      Lacoste, Alexandre",
    booktitle = "Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.realm-1.27/",
    pages = "367--385",
    ISBN = "979-8-89176-264-0",
    abstract = "Large language models (LLMs) are increasingly used as autonomous agents, tackling tasks from robotics to web navigation. Their performance depends on the underlying `base agent{`}. Existing methods, however, struggle with long-context reasoning and goal adherence. We introduce `StateAct{`}, a novel and efficient `base agent{`} that enhances decision-making through (1) `self-prompting{`}, which reinforces task goals at every step, and (2) `chain-of-states{`}, an extension of chain-of-thought that tracks state information over time. StateAct outperforms ReAct, the previous best `base agent{`}, by over 10{\%} on Alfworld, 30{\%} on Textcraft, and 7{\%} on Webshop across multiple frontier LLMs. We also demonstrate that StateAct can be used as a drop-in replacement for ReAct with with advanced LLM agent methods such as test-time scaling, yielding an additional 12{\%} gain on Textcraft. By improving efficiency and long-range reasoning without requiring additional training or retrieval, StateAct provides a scalable foundation for LLM agents. We open source our code to support further research at https://github.com/ai-nikolai/stateact."
}