Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation

Researchers reformulated the autoresearch pattern as a stateful ReAct agent using LangGraph, achieving 90% fewer tokens on hyperparameter tuning and 52% fewer on code optimization compared to stateless designs. The stateful agent operates within a fixed-size conversation window, reducing token costs from O(n) to O(1) per iteration while maintaining optimization quality.

arXiv:2606.14945v1 Announce Type: new Abstract: The autoresearch pattern enables autonomous experimentation by having a large language model LLM iteratively modify code to optimize a target metric. Its stateless design, however, reconstructs experimental context from scratch at every iteration, incurring $O n $ token cost per iteration and $O n^{2} $ total. This work reformulates the pattern as a stateful ReAct agent using LangGraph, where typed persistent state carries experimental history across iterations via a tool-calling interface. Two benchmarks are evaluated: hyperparameter tuning 15 iterations, small per-iteration observations and code performance optimization 40 iterations, large per-iteration observations containing full source code and benchmark results . On hyperparameter tuning, the stateful agent consumes 90\% fewer tokens 2{,}492 vs.\ 24{,}465 . On code optimization, the stateful agent consumes 52\% fewer tokens 627K vs.\ 1{,}275K while achieving comparable optimization quality on both tasks. The token reduction is structural: the stateless agent re-reads the full history at $O n $ cost per iteration, while the stateful agent operates within a fixed-size conversation window at $O 1 $ cost. This paper describes the architecture in sufficient detail for practitioners to implement a stateful autoresearch agent for their own workflows.