StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking

TL;DR

StateAct is a new base agent for large language models that improves decision-making through self-prompting and state-tracking, significantly outperforming previous methods across multiple tasks without extra training.

Contribution

It introduces StateAct, a novel agent combining self-prompting and chain-of-states, enhancing reasoning and goal adherence without additional training or retrieval.

Findings

Outperforms ReAct by over 10% on Alfworld

Achieves 30% improvement on Textcraft

Provides a scalable, efficient foundation for LLM agents

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 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 .