mlsanityData to 14 Oct 2026

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

arXiv 2505.15182 ↗First posted 21 May 2025cs.CL cs.AI cs.LGcited by 31

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 23 of its 43 references that are in the map. First posted on arXiv 21 May 2025.

Builds on

23 of 43 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025MPO: Boosting LLM Agents with Meta Plan Optimization4 Mar
  2. 2024Agent Planning with World Knowledge Model23 May
  3. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents24 Jan
  4. 2023Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency29 Sep
  5. 2023Agents: An Open-source Framework for Autonomous Language Agents14 Sep
  6. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May

Other references · 17

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  4. 2018World Modelscited by 1,513
  5. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  6. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  7. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  8. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  9. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 465
  10. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 327
  11. 2025Reasoning Models Can Be Effective Without Thinkingcited by 187
  12. 2019Interactive Fiction Games: A Colossal Adventurecited by 168
5 more
  1. 2024BALROG: Benchmarking Agentic LLM and VLM Reasoning On Gamescited by 146
  2. 2025Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2cited by 97
  3. 2024StateFlow: Enhancing LLM Task-Solving through State-Driven Workflowscited by 65
  4. 2016Control of Memory, Active Perception, and Action in Minecraftcited by 61
  5. 2025A Survey on Mathematical Reasoning and Optimization with Large Language Modelscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 25.

31 papers.

Sort:

By area:

  1. 2026SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revisioncited by 30
  2. 2026Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimizationcited by 19
  3. 2026DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generationcited by 18
  4. 2025The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systemscited by 14
  5. 2025Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Factscited by 13
  6. 2026Self-Evolving World Models for LLM Agent Planningcited by 13
  7. 2026Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertaintycited by 9
  8. 2026Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnessescited by 9
  9. 2026PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environmentscited by 7
  10. 2026AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraintscited by 7
  11. 2026Retrospective Progress-Aware Self-Refinement for LLM Agent Trainingcited by 6
  12. 2026SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent Systemcited by 5
19 more
  1. 2026When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agentscited by 5
  2. 2026TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agentscited by 4
  3. 2026Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversationscited by 3
  4. 2025Can Lessons From Human Teams Be Applied to Multi-Agent Systems? The Role of Structure, Diversity, and Interaction Dynamicscited by 2
  5. 2025ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routingcited by 2
  6. 2026Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agentscited by 2
  7. 2026Co-Evolution of Policy and Internal Reward for Language Agentscited by 1
  8. 2026Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agentscited by 1
  9. 2026Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agentscited by 1
  10. 2026Unified Context Evolution for LLM Agentscited by 1
  11. 2026Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agentscited by 1
  12. 2026HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM Agentscited by 1
  13. 2025Strategic Reflectivism In Intelligent Systemscited by 0
  14. 2025Align While Search: Belief-Guided Exploratory Inference for World-Grounded Embodied Agentscited by 0
  15. 2026Latent Action Reparameterization for Efficient Agent Inferencecited by 0
  16. 2026What to Format and How: A Benchmark and Workflow Approach for Document Formattingcited by 0
  17. 2026SGG-ReflAct: Sub-Goal Guided ReflAct with Structured Planning for Reliable Long-Horizon Reasoningcited by 0
  18. 2026Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief Statescited by 0
  19. 2026CB-Agent: Concept-Based In-Context Learning for Sequential Action Selectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents
  2. 2025COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
  3. 2025Reflecting with Two Voices: A Co-Adaptive Dual-Strategy Framework for LLM-Based Agent Decision Making
  4. 2026From Task Solving to Robust Real-World Adaptation in LLM Agents
  5. 2026Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents
  6. 2026Consistent Plan-Act for Long-Horizon Agentic Tasks
  7. 2026Inducing Reasoning Primitives from Agent Traces
  8. 2026Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis