返回首页
arXiv AI··论文与技术

DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents

中文摘要

DeReAct 是一种模块化 AI 代理架构,通过将推理与行动分解并引入 Critic 验证机制,提升了任务执行的可靠性与控制力。

English Summary

DeReAct is a modular AI agent architecture that decomposes reasoning and acting using external gating policies to enhance reliability and action control.

原文节选

arXiv:2610.02351v1 Announce Type: new Abstract: ReAct-based agents typically rely on a single LLM policy to propose actions, interact with the environment, and decide when a task is complete. This coupling makes action authorization and completion control difficult to enforce independently, allowing errors to propagate and unsupported completion claims to terminate execution. We introduce DeReAct, a modular agent architecture that externalizes two gating policies: a Critic that validates proposed actions before execution, and a Context Manager that reconstructs an environment-supported \textsc{State} and certifies task completion. Across GAIA and SWE-bench Verified, DeReAct improves Pass@1 most for weaker Brain models, with gains of 6.5--7.0 points for Qwen3-Coder-480B and 4.2--5.2 points for Claude Sonnet~4.5; gains diminish as Brain capability increases. Trajectory and ablation analyses show that external gating is effective when targeted failures are sufficiently prevalent and the gating policy is itself sufficient. With Claude Opus~4.5, Pass@1 remains comparable to ReAct, while DeReAct produces more evidence-complete and constraint-satisfying trajectories, indicating that compl…