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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Jeonghye, Rhee, Sojeong, Kim, Minbeom, Kim, Dohyung, Lee, Sangmook, Sung, Youngchul, Jung, Kyomin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918149466619904
author Kim, Jeonghye
Rhee, Sojeong
Kim, Minbeom
Kim, Dohyung
Lee, Sangmook
Sung, Youngchul
Jung, Kyomin
author_facet Kim, Jeonghye
Rhee, Sojeong
Kim, Minbeom
Kim, Dohyung
Lee, Sangmook
Sung, Youngchul
Jung, Kyomin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15182
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
Kim, Jeonghye
Rhee, Sojeong
Kim, Minbeom
Kim, Dohyung
Lee, Sangmook
Sung, Youngchul
Jung, Kyomin
Computation and Language
Artificial Intelligence
Machine Learning
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.
title ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.15182