ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection

TL;DR

ReflAct introduces a goal-state reflection mechanism into LLM agents, significantly improving their reasoning consistency and success rates by maintaining better internal belief and goal alignment.

Contribution

It proposes ReflAct, a novel reasoning backbone that emphasizes continuous reflection and grounding in goal states, outperforming existing methods like ReAct.

Findings

ReflAct surpasses ReAct by 27.7% on average.

Achieves 93.3% success rate in ALFWorld.

Outperforms enhanced ReAct variants, emphasizing core reasoning improvements.

Abstract

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.