Self-Reflection in Large Language Model Agents: Effects on Problem-Solving Performance
Abstract
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
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Reflection mechanisms' corrective efficacy remains at the level of trajectories and has not yet yielded knowledge at the level of strategy that is transferable.
“their corrective efficacy remains at the level of trajectories and has not yet yielded knowledge at the level of strategy that is transferable (Shinn et al., 2023; Renze and Guven, 2024).”
From From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms (2026) · cites this paper as Renze and Guven, 2024
Cites
AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
Zhong, W., Cui, R., Guo, Y., Liang, Y., Lu, S., Wang, Y., Saied, A., Chen, W., & Duan, N. (2023) · arXiv · doi:10.48550/arxiv.2304.06364 · Cited by 211 · see citing works
SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
Miao, N., Teh, Y. W., & Rainforth, T. (2023) · arXiv · doi:10.48550/arxiv.2308.00436 · Cited by 18 · cited 3× · see citing works
“In addition, they’ve been observed successfully using tools, including web browsers, search engines, code interpreters, etc. [10], [19]–[21].”
Flagged first, then by citations
Cited by
Sorted by citations
A Survey on the Optimization of Large Language Model-based Agents
Du, S., Zhao, J., Shi, J., Xie, Z., Jiang, X., Bai, Y., & He, L. (2025) · arXiv · doi:10.48550/arxiv.2503.12434 · Cited by 22
Private Yet Social: How LLM Chatbots Support and Challenge Eating Disorder Recovery
Choi, R., Kim, T., Park, S., Kim, J. G., & Lee, S.-J. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713485 · Cited by 19 · see citing works
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
Luo, J., Tian, Y., Cao, C., Luo, Z., Lin, H., Li, K., Kong, C., Yang, R., & Ma, J. (2026) · Findings of the Association for Computational Linguistics: ACL 2026 · doi:10.18653/v1/2026.findings-acl.2069 · Cited by 3 · see citing works
Hossen, M. S., Jahan, T., Barua, A., & Opel, M. Z. K. (2025) · 2025 IEEE 4th International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things (RAAICON) · doi:10.1109/raaicon69033.2025.11502408
- Authors
- Renze, M., & Guven, E.
- Affiliations
- Johns Hopkins University (US)
- Venue
- 2024 2nd International Conference on Foundation and Large Language Models (FLLM)
- Publisher
- IEEE
- Published
- 2024-11-26
- Pages
- 516-525
- OpenAlex
- W4406892424
- Cited by
- 58
- References
- 2
- Citations by year
- 2026: 26 · 2025: 32
- FWCI
- 14.02
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Foundation and Large Language Models (FLLM) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- self-reflection, large language models, LLM agents, problem-solving performance, human development, multiple-choice questions, meta-learning, self-directed learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
