mlsanityData to 14 Oct 2026

Can Large Language Models Really Improve by Self-critiquing Their Own Plans?

arXiv 2310.08118 ↗First posted 12 Oct 2023cs.AIcited by 108

Not on the map. Why?

Cited by 39 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

There have been widespread claims about Large Language Models (LLMs) being able to successfully verify or self-critique their candidate solutions in reasoning problems in an iterative mode. Intrigued by those claims, in this paper we set out to investigate the verification/self-critiquing abilities of large language models in the context of planning. We evaluate a planning system that employs LLMs for both plan generation and verification. We assess the verifier LLM's performance against ground-truth verification, the impact of self-critiquing on plan generation, and the influence of varying feedback levels on system performance. Using GPT-4, a state-of-the-art LLM, for both generation and verification, our findings reveal that self-critiquing appears to diminish plan generation performance, especially when compared to systems with external, sound verifiers and the LLM verifiers in that system produce a notable number of false positives, compromising the system's reliability. Additionally, the nature of feedback, whether binary or detailed, showed minimal impact on plan generation. Collectively, our results cast doubt on the effectiveness of LLMs in a self-critiquing, iterative framework for planning tasks.

Key facts. Cited by 108 papers in the map (data through 14 Oct 2026). Builds on 7 of its 13 references that are in the map. First posted on arXiv 12 Oct 2023.

Builds on

7 of 13 references.

References · 7

  1. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  2. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  4. 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 503
  5. 2023Language Models can Solve Computer Taskscited by 372
  6. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 312
  7. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 156

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 12; 2024: 48; 2025: 36; 2026: 12.

108 papers.

Sort:

By area:

  1. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  3. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 465
  4. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 288
  5. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 179
  6. 2024The pitfalls of next-token predictioncited by 160
  7. 2024Marco-o1: Towards Open Reasoning Models for Open-Ended Solutionscited by 144
  8. 2024Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinementcited by 114
  9. 2025Confidence Improves Self-Consistency in LLMscited by 113
  10. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 111
  11. 2023Learning From Mistakes Makes LLM Better Reasonercited by 101
  12. 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communicationcited by 82
38 more
  1. 2024Can Large Language Models Reason and Plan?cited by 82
  2. 2024Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systemscited by 81
  3. 2025Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectoriescited by 81
  4. 2024Visibility into AI Agentscited by 79
  5. 2023Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generationcited by 74
  6. 2024Self-Evolving Multi-Agent Collaboration Networks for Software Developmentcited by 74
  7. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  8. 2024Self-Contrast: Better Reflection Through Inconsistent Solving Perspectivescited by 71
  9. 2023CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generationcited by 66
  10. 2025Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitatecited by 63
  11. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agentscited by 61
  12. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 57
  13. 2025Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?cited by 54
  14. 2023LLatrieval: LLM-Verified Retrieval for Verifiable Generationcited by 52
  15. 2025Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verificationcited by 50
  16. 2023Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioningcited by 49
  17. 2024Beyond Preferences in AI Alignmentcited by 49
  18. 2024Enhance Reasoning for Large Language Models in the Game Werewolfcited by 46
  19. 2025Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMscited by 46
  20. 2024Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correctioncited by 45
  21. 2024A Theoretical Understanding of Self-Correction through In-context Alignmentcited by 44
  22. 2025Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluatorscited by 44
  23. 2023CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Updatecited by 43
  24. 2023A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoningcited by 41
  25. 2024On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)cited by 40
  26. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoningcited by 40
  27. 2025LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Modelscited by 38
  28. 2024Are Large Language Models Good Prompt Optimizers?cited by 37
  29. 2024LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environmentscited by 32
  30. 2025Robotouille: An Asynchronous Planning Benchmark for LLM Agentscited by 32
  31. 2025Self Speculative Decoding for Diffusion Large Language Modelscited by 30
  32. 2024Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMscited by 29
  33. 2025Roll the dice & look before you leap: Going beyond the creative limits of next-token predictioncited by 29
  34. 2023DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendationcited by 27
  35. 2024SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responsescited by 26
  36. 2024Spontaneous Reward Hacking in Iterative Self-Refinementcited by 26
  37. 2024KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Modelscited by 24
  38. 2025Stay Focused: Problem Drift in Multi-Agent Debatecited by 23

50 most cited of 108 All 108 (JSON)