让大模型智能体持续反思自身状态与目标的差距，提升决策可靠性。
ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
- 通过持续反思当前状态与目标的差距来优化决策
- 在ALFWorld任务中达到93.3%成功率，比ReAct高27.7%
- 适合需要长期规划与状态对齐的复杂任务场景
近期大型语言模型（LLM）智能体的发展主要基于如ReAct的推理框架，该框架在复杂环境中交替进行思考与行动。然而，ReAct常产生脱离现实或逻辑不一致的推理步骤，导致智能体实际状态与目标之间出现偏差。分析表明，这源于ReAct无法维持一致的内部信念和目标对齐，从而引发错误累积和幻觉。为此，我们提出ReflAct，一种新推理框架，将推理重点从单纯规划下一步动作，转变为持续反思当前状态与目标之间的关系。通过显式地以状态为基础并持续确保目标对齐，ReflAct显著提升了策略可靠性。实证结果显示，ReflAct平均超越ReAct 27.7%，在ALFWorld任务中达到93.3%的成功率。值得注意的是，即使在添加增强模块（如Reflexion、WKM）的ReAct基础上，ReflAct仍表现更优，说明强化核心推理机制是实现可靠智能体性能的关键。
原文摘要 · Abstract (English)
Recent advances in LLM agents have largely built on reasoning backbones like ReAct, which interleave thought and action in complex environments. However, ReAct often produces ungrounded or incoherent reasoning steps, leading to misalignment between the agent's actual state and goal. Our analysis finds that this stems from ReAct's inability to maintain consistent internal beliefs and goal alignment, causing compounding errors and hallucinations. To address this, we introduce ReflAct, a novel backbone that shifts reasoning from merely planning next actions to continuously reflecting on the agent's state relative to its goal. By explicitly grounding decisions in states and enforcing ongoing goal alignment, ReflAct dramatically improves strategic reliability. This design delivers substantial empirical gains: ReflAct surpasses ReAct by 27.7% on average, achieving a 93.3% success rate in ALFWorld. Notably, ReflAct even outperforms ReAct with added enhancement modules (e.g., Reflexion, WKM), showing that strengthening the core reasoning backbone is key to reliable agent performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。