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

arXiv: https://arxiv.org/abs/2310.08118 · HTML: https://mlsanity.com/paper/2310.08118/

## 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 (most cited first, 7 of 7)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Faith and Fate: Limits of Transformers on Compositionality](https://mlsanity.com/paper/2305.18654/) (2023)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [LM vs LM: Detecting Factual Errors via Cross Examination](https://mlsanity.com/paper/2305.13281/) (2023)

## Built on by (most cited first, 30 of 108)

- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [R-Judge: Benchmarking Safety Risk Awareness for LLM Agents](https://mlsanity.com/paper/2401.10019/) (2024)
- [LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks](https://mlsanity.com/paper/2402.01817/) (2024)
- [The pitfalls of next-token prediction](https://mlsanity.com/paper/2403.06963/) (2024)
- [Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions](https://mlsanity.com/paper/2411.14405/) (2024)
- [Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement](https://mlsanity.com/paper/2402.11436/) (2024)
- [Confidence Improves Self-Consistency in LLMs](https://mlsanity.com/paper/2502.06233/) (2025)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [Learning From Mistakes Makes LLM Better Reasoner](https://mlsanity.com/paper/2310.20689/) (2023)
- [Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication](https://mlsanity.com/paper/2312.01823/) (2023)
- [Can Large Language Models Reason and Plan?](https://mlsanity.com/paper/2403.04121/) (2024)
- [Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems](https://mlsanity.com/paper/2407.13032/) (2024)
- [Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories](https://mlsanity.com/paper/2506.18824/) (2025)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation](https://mlsanity.com/paper/2311.04254/) (2023)
- [Self-Evolving Multi-Agent Collaboration Networks for Software Development](https://mlsanity.com/paper/2410.16946/) (2024)
- [Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents](https://mlsanity.com/paper/2311.11797/) (2023)
- [Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives](https://mlsanity.com/paper/2401.02009/) (2024)
- [CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation](https://mlsanity.com/paper/2311.18702/) (2023)
- [Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate](https://mlsanity.com/paper/2501.17703/) (2025)
- [KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents](https://mlsanity.com/paper/2403.03101/) (2024)
- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?](https://mlsanity.com/paper/2502.00674/) (2025)
- [LLatrieval: LLM-Verified Retrieval for Verifiable Generation](https://mlsanity.com/paper/2311.07838/) (2023)
- [Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification](https://mlsanity.com/paper/2502.01839/) (2025)
- [Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning](https://mlsanity.com/paper/2312.10160/) (2023)
- [Beyond Preferences in AI Alignment](https://mlsanity.com/paper/2408.16984/) (2024)
- [Enhance Reasoning for Large Language Models in the Game Werewolf](https://mlsanity.com/paper/2402.02330/) (2024)

## 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.