StateAct: enhancing LLM base agents via self-prompting and state-tracking
File(s)
Preprint version
OA Location
Author(s)
Rozanov, Nikolai
Rei, Marek
Type
preprint
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 longcontext 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 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.
Date Issued
2025-04-08
Citation
arXiv, 2025
Journal / Book Title
arXiv
Copyright Statement
Copyright © 2025 The Author(s). This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
License URL
Description
Preprint version
Identifier
http://arxiv.org/abs/2410.02810v3
Subjects
cs.AI
cs.AI
cs.CL
cs.LG