mlsanityData to 14 Oct 2026

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

arXiv 2405.06682 ↗First posted 5 May 2024cs.CL cs.AIcited by 39

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

Abstract (arXiv)

In this study, we investigated the effects of self-reflection in large language models (LLMs) on problem-solving performance. We instructed nine popular LLMs to answer a series of multiple-choice questions to provide a performance baseline. For each incorrectly answered question, we instructed eight types of self-reflecting LLM agents to reflect on their mistakes and provide themselves with guidance to improve problem-solving. Then, using this guidance, each self-reflecting agent attempted to re-answer the same questions. Our results indicate that LLM agents are able to significantly improve their problem-solving performance through self-reflection (p < 0.001). In addition, we compared the various types of self-reflection to determine their individual contribution to performance. All code and data are available on GitHub at https://github.com/matthewrenze/self-reflection

Key facts. Cited by 39 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 40 of its 57 references that are in the map. First posted on arXiv 5 May 2024.

Builds on

40 of 57 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior9 Jan
  2. 2023Agent Instructs Large Language Models to be General Zero-Shot Reasoners5 Oct
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep

Other references · 37

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  8. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  10. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  11. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  12. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
25 more
  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  3. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  6. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  7. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  8. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 716
  9. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 619
  10. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  11. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 543
  12. 2024Large Language Models: A Surveycited by 525
  13. 2023Augmented Language Models: a Surveycited by 403
  14. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  15. 2020Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learningcited by 216
  16. 2024The Effect of Sampling Temperature on Problem Solving in Large Language Modelscited by 170
  17. 2023SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoningcited by 159
  18. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tangocited by 128
  19. 2023LLMs cannot find reasoning errors, but can correct them given the error locationcited by 85
  20. 2023Towards Mitigating Hallucination in Large Language Models via Self-Reflectioncited by 81
  21. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generationcited by 75
  22. 2023Metacognitive Prompting Improves Understanding in Large Language Modelscited by 58
  23. 2023Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4cited by 48
  24. 2021From LSAT: The Progress and Challenges of Complex Reasoningcited by 43
  25. 2023How susceptible are LLMs to Logical Fallacies?cited by 23

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 23; 2026: 10.

39 papers.

Sort:

By area:

  1. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 610
  2. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  3. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  4. 2024Large Language Model-Brained GUI Agents: A Surveycited by 162
  5. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
  6. 2024A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Educationcited by 16
  7. 2024Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seekingcited by 16
  8. 2024SAUP: Situation Awareness Uncertainty Propagation on LLM Agentcited by 14
  9. 2025ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoningcited by 13
  10. 2025SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generationcited by 12
  11. 2025AdapThink: Adaptive Thinking Preferences for Reasoning Language Modelcited by 11
  12. 2025Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoningcited by 10
27 more
  1. 2025R-TOFU: Unlearning in Large Reasoning Modelscited by 9
  2. 2025Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learningcited by 8
  3. 2025Self-Aligned Reward: Towards Effective and Efficient Reasonerscited by 7
  4. 2025Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysiscited by 6
  5. 2025Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systemscited by 6
  6. 2026Brain-Inspired Graph Multi-Agent Systems for LLM Reasoningcited by 6
  7. 2025Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Taskscited by 4
  8. 2025Can Past Experience Accelerate LLM Reasoning?cited by 3
  9. 2026Unified Data Selection for LLM Reasoningcited by 3
  10. 2024Meta-Reflection: A Feedback-Free Reflection Learning Frameworkcited by 2
  11. 2025DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoningcited by 2
  12. 2025Unleashing Diverse Thinking Modes in LLMs through Multi-Agent Collaborationcited by 2
  13. 2025Enhancing Vision-Language Models for Autonomous Driving through Task-Specific Prompting and Spatial Reasoningcited by 2
  14. 2025MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuningcited by 2
  15. 2025Advancing Multi-Step Mathematical Reasoning in Large Language Models through Multi-Layered Self-Reflection with Auto-Promptingcited by 1
  16. 2025Reasoning Beyond the Obvious: Evaluating Divergent and Convergent Thinking in LLMs for Financial Scenarioscited by 1
  17. 2025Cube Bench: A Benchmark for Spatial Visual Reasoning in MLLMscited by 1
  18. 2026Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDPcited by 1
  19. 2026Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivotscited by 1
  20. 2024MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoningcited by 0
  21. 2025MARCO: Meta-Reflection with Cross-Referencing for Code Reasoningcited by 0
  22. 2025Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoningcited by 0
  23. 2026A Comprehensive Evaluation of LLM Reasoning: From Single-Model to Multi-Agent Paradigmscited by 0
  24. 2026Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoningcited by 0
  25. 2026LinTree: Improving LLM Reasoning with Explicitly Structured Search Historiescited by 0
  26. 2026NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observabilitycited by 0
  27. 2026How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning Benchmarkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models
  2. 2024Self-Reflection Makes Large Language Models Safer, Less Biased, and Ideologically Neutral
  3. 2024Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives
  4. 2025Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
  5. 2025MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs
  6. 2026Enhancing LLM Problem Solving via Tutor-Student Multi-Agent Interaction
  7. 2025Agentic Large Language Models, a survey
  8. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate