<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rozanov-rei-2025-stateact">
    <titleInfo>
        <title>StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nikolai</namePart>
        <namePart type="family">Rozanov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marek</namePart>
        <namePart type="family">Rei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Kamalloo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicolas</namePart>
            <namePart type="family">Gontier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xing</namePart>
            <namePart type="given">Han</namePart>
            <namePart type="family">Lu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nouha</namePart>
            <namePart type="family">Dziri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shikhar</namePart>
            <namePart type="family">Murty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alexandre</namePart>
            <namePart type="family">Lacoste</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-264-0</identifier>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">rozanov-rei-2025-stateact</identifier>
    <identifier type="doi">10.18653/v1/2025.realm-1.27</identifier>
    <location>
        <url>https://aclanthology.org/2025.realm-1.27/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>367</start>
            <end>385</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
%A Rozanov, Nikolai
%A Rei, Marek
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Lu, Xing Han
%Y Dziri, Nouha
%Y Murty, Shikhar
%Y Lacoste, Alexandre
%S Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-264-0
%F rozanov-rei-2025-stateact
%X 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.
%R 10.18653/v1/2025.realm-1.27
%U https://aclanthology.org/2025.realm-1.27/
%U https://doi.org/10.18653/v1/2025.realm-1.27
%P 367-385

Markdown (Informal)

[StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking](https://aclanthology.org/2025.realm-1.27/) (Rozanov & Rei, REALM 2025)

• StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking (Rozanov & Rei, REALM 2025)

ACL

• Nikolai Rozanov and Marek Rei. 2025. StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking. In Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025), pages 367–385, Vienna, Austria. Association for Computational Linguistics.