Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance (2405.06682v3)

Published 5 May 2024 in cs.CL and cs.AI

Abstract: In this study, we investigated the effects of self-reflection in 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

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. T. Kojima, S. S. Gu, M. Reid, Y. Matsuo, and Y. Iwasawa, “Large language models are zero-shot reasoners,” in Advances in Neural Information Processing Systems, vol. 35, 5 2022, pp. 22 199–22 213. [Online]. Available: https://arxiv.org/abs/2205.11916
  2. J. Wei, X. Wang, D. Schuurmans, M. Bosma, B. Ichter, F. Xia, E. Chi, Q. Le, and D. Zhou, “Chain-of-thought prompting elicits reasoning in large language models,” arXiv, 1 2022. [Online]. Available: https://arxiv.org/abs/2201.11903
  3. Y. Zhou, A. I. Muresanu, Z. Han, K. Paster, S. Pitis, H. Chan, and J. Ba, “Large language models are human-level prompt engineers,” The Eleventh International Conference on Learning Representations, 11 2023. [Online]. Available: https://arxiv.org/abs/2211.01910
  4. Z. Ji, N. Lee, R. Frieske, T. Yu, D. Su, Y. Xu, E. Ishii, Y. Bang, D. Chen, H. S. Chan, W. Dai, A. Madotto, and P. Fung, “Survey of hallucination in natural language generation,” ACM Computing Surveys, vol. 55, 2 2022. [Online]. Available: http://dx.doi.org/10.1145/3571730
  5. M. U. Hadi, qasem al tashi, R. Qureshi, A. Shah, amgad muneer, M. Irfan, A. Zafar, M. B. Shaikh, N. Akhtar, J. Wu, S. Mirjalili, Q. Al-Tashi, and A. Muneer, “A survey on large language models: Applications, challenges, limitations, and practical usage,” Authorea Preprints, 10 2023. [Online]. Available: https://doi.org/10.36227/techrxiv.23589741.v1
  6. A. Payandeh, D. Pluth, J. Hosier, X. Xiao, and V. K. Gurbani, “How susceptible are llms to logical fallacies?” arXiv, 8 2023. [Online]. Available: https://arxiv.org/abs/2308.09853v1
  7. J. Huang, X. Chen, S. Mishra, H. S. Zheng, A. W. Yu, X. Song, and D. Zhou, “Large language models cannot self-correct reasoning yet,” arXiv, 10 2023. [Online]. Available: https://arxiv.org/abs/2310.01798
  8. Z. Ji, T. Yu, Y. Xu, N. Lee, E. Ishii, and P. Fung, “Towards mitigating hallucination in large language models via self-reflection,” arXiv, 10 2023. [Online]. Available: https://arxiv.org/abs/2310.06271
  9. S. Minaee, T. Mikolov, N. Nikzad, M. Chenaghlu, R. Socher, X. Amatriain, and J. Gao, “Large language models: A survey,” arXiv, 2 2024. [Online]. Available: https://arxiv.org/abs/2402.06196
  10. N. Shinn, F. Cassano, E. Berman, A. Gopinath, K. Narasimhan, and S. Yao, “Reflexion: Language agents with verbal reinforcement learning,” arXiv, 3 2023. [Online]. Available: https://arxiv.org/abs/2303.11366
  11. L. Pan, M. Saxon, W. Xu, D. Nathani, X. Wang, and W. Y. Wang, “Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies,” arXiv, 8 2023. [Online]. Available: https://arxiv.org/abs/2308.03188
  12. A. Madaan, N. Tandon, P. Gupta, S. Hallinan, L. Gao, S. Wiegreffe, U. Alon, N. Dziri, S. Prabhumoye, Y. Yang, S. Gupta, B. P. Majumder, K. Hermann, S. Welleck, A. Yazdanbakhsh, and P. Clark, “Self-refine: Iterative refinement with self-feedback,” arXiv, 3 2023. [Online]. Available: https://arxiv.org/abs/2303.17651v2
  13. J. Toy, J. MacAdam, and P. Tabor, “Metacognition is all you need? using introspection in generative agents to improve goal-directed behavior,” arXiv, 1 2024. [Online]. Available: https://arxiv.org/abs/2401.10910
  14. Y. Wang and Y. Zhao, “Metacognitive prompting improves understanding in large language models,” arXiv, 8 2023. [Online]. Available: https://arxiv.org/abs/2308.05342
  15. A. Asai, Z. Wu, Y. Wang, A. Sil, and H. Hajishirzi, “Self-rag: Learning to retrieve, generate, and critique through self-reflection,” arXiv, 10 2023. [Online]. Available: https://arxiv.org/abs/2310.11511v1
  16. G. Wang, Y. Xie, Y. Jiang, A. Mandlekar, C. Xiao, Y. Zhu, A. Anandkumar, U. Austin, and U. Madison, “Voyager: An open-ended embodied agent with large language models,” arXiv, 5 2023. [Online]. Available: https://arxiv.org/abs/2305.16291v2
  17. Z. Xi, W. Chen, X. Guo, W. He, Y. Ding, B. Hong, M. Zhang, J. Wang, S. Jin, E. Zhou, R. Zheng, X. Fan, X. Wang, L. Xiong, Y. Zhou, W. Wang, C. Jiang, Y. Zou, X. Liu, Z. Yin, S. Dou, R. Weng, W. Cheng, Q. Zhang, W. Qin, Y. Zheng, X. Qiu, X. Huang, and T. Gui, “The rise and potential of large language model based agents: A survey,” arXiv, 9 2023. [Online]. Available: https://arxiv.org/abs/2309.07864v3
  18. S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao, “React: Synergizing reasoning and acting in language models,” arXiv, 10 2022. [Online]. Available: https://arxiv.org/abs/2210.03629
  19. N. Miao, Y. W. Teh, and T. Rainforth, “Selfcheck: Using llms to zero-shot check their own step-by-step reasoning,” arXiv, 8 2023. [Online]. Available: https://arxiv.org/abs/2308.00436v3
  20. R. Nakano, J. Hilton, S. Balaji, J. Wu, L. Ouyang, C. Kim, C. Hesse, S. Jain, V. Kosaraju, W. Saunders, X. Jiang, K. Cobbe, T. Eloundou, G. Krueger, K. Button, M. Knight, B. Chess, and J. S. Openai, “Webgpt: Browser-assisted question-answering with human feedback,” arXiv, 12 2021. [Online]. Available: https://arxiv.org/abs/2112.09332v3
  21. T. Schick, J. Dwivedi-Yu, R. Dessì, R. Raileanu, M. Lomeli, L. Zettlemoyer, N. Cancedda, and T. Scialom, “Toolformer: Language models can teach themselves to use tools,” arXiv, 2 2023. [Online]. Available: https://arxiv.org/abs/2302.04761v1
  22. P. Lewis and et al., “Retrieval-augmented generation for knowledge-intensive nlp tasks,” arXiv, 5 2020. [Online]. Available: https://arxiv.org/abs/2005.11401
  23. Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, Y. Dai, J. Sun, M. Wang, and H. Wang, “Retrieval-augmented generation for large language models: A survey,” arXiv, 12 2023. [Online]. Available: https://arxiv.org/abs/2312.10997v5
  24. W. Zhong, L. Guo, Q. Gao, H. Ye, and Y. Wang, “Memorybank: Enhancing large language models with long-term memory,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 19 724–19 731, 5 2023. [Online]. Available: https://arxiv.org/abs/2305.10250v3
  25. Z. Wang, A. Liu, H. Lin, J. Li, X. Ma, and Y. Liang, “Rat: Retrieval augmented thoughts elicit context-aware reasoning in long-horizon generation,” arXiv, 3 2024. [Online]. Available: https://arxiv.org/abs/2403.05313
  26. G. Tyen, H. Mansoor, V. Cărbune, P. Chen, and T. Mak, “Llms cannot find reasoning errors, but can correct them!” arXiv, 11 2023. [Online]. Available: https://arxiv.org/abs/2311.08516v2
  27. P. Clark, I. Cowhey, O. Etzioni, T. Khot, A. Sabharwal, C. Schoenick, and O. Tafjord, “Think you have solved question answering? try arc, the ai2 reasoning challenge,” ArXiv, 3 2018. [Online]. Available: https://arxiv.org/abs/1803.05457
  28. R. Zellers, A. Holtzman, Y. Bisk, A. Farhadi, and Y. Choi, “Hellaswag: Can a machine really finish your sentence?” in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019. [Online]. Available: https://arxiv.org/abs/1905.07830
  29. A. Pal, L. K. Umapathi, and M. Sankarasubbu, “Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering,” in Proceedings of the Conference on Health, Inference, and Learning.   PMLR, 2022, pp. 248–260. [Online]. Available: https://proceedings.mlr.press/v174/pal22a.html
  30. W. Zhong, R. Cui, Y. Guo, Y. Liang, S. Lu, Y. Wang, A. Saied, W. Chen, and N. Duan, “Agieval: A human-centric benchmark for evaluating foundation models,” ArXiv, 4 2023. [Online]. Available: https://arxiv.org/abs/2304.06364
  31. J. Liu, L. Cui, H. Liu, D. Huang, Y. Wang, and Y. Zhang, “Logiqa: A challenge dataset for machine reading comprehension with logical reasoning,” in International Joint Conference on Artificial Intelligence, 2020. [Online]. Available: https://arxiv.org/abs/2007.08124
  32. S. Wang, Z. Liu, W. Zhong, M. Zhou, Z. Wei, Z. Chen, and N. Duan, “From lsat: The progress and challenges of complex reasoning,” IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 30, pp. 2201–2216, 8 2021. [Online]. Available: https://doi.org/10.1109/TASLP.2022.3164218
  33. Anthropic, “Introducing the next generation of claude  anthropic,” 2024. [Online]. Available: https://www.anthropic.com/news/claude-3-family
  34. ——, “The claude 3 model family: Opus, sonnet, haiku,” 2024. [Online]. Available: https://www.anthropic.com/claude-3-model-card
  35. Cohere, “Command r+,” 2024. [Online]. Available: https://docs.cohere.com/docs/command-r-plus
  36. ——, “Model card for c4ai command r+,” 2024. [Online]. Available: https://huggingface.co/CohereForAI/c4ai-command-r-plus
  37. S. Pichai and D. Hassabis, “Introducing gemini: Google’s most capable ai model yet,” 2023. [Online]. Available: https://blog.google/technology/ai/google-gemini-ai/
  38. Gemini-Team, “Gemini: A family of highly capable multimodal models,” arXiv, 12 2023.
  39. S. Pichai and D. Hassabis, “Introducing gemini 1.5, google’s next-generation ai model,” 2024. [Online]. Available: https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/
  40. Gemini-Team, “Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context,” 2024. [Online]. Available: https://arxiv.org/abs/2403.05530
  41. OpenAI, “Introducing chatgpt,” 11 2022. [Online]. Available: https://openai.com/blog/chatgpt
  42. ——, “Models - openai api.” [Online]. Available: https://platform.openai.com/docs/models/gpt-3-5-turbo
  43. ——, “Gpt-4,” 3 2023. [Online]. Available: https://openai.com/research/gpt-4
  44. ——, “Gpt-4 technical report,” arXiv, 3 2023. [Online]. Available: https://arxiv.org/abs/2303.08774
  45. Meta, “Meta and microsoft introduce the next generation of llama | meta,” 2023. [Online]. Available: https://about.meta.com/news/2023/07/llama-2/
  46. H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale, D. Bikel, L. Blecher, C. C. Ferrer, M. Chen, G. Cucurull, D. Esiobu, J. Fernandes, J. Fu, W. Fu, B. Fuller, C. Gao, V. Goswami, N. Goyal, A. Hartshorn, S. Hosseini, R. Hou, H. Inan, M. Kardas, V. Kerkez, M. Khabsa, I. Kloumann, A. Korenev, P. S. Koura, M.-A. Lachaux, T. Lavril, J. Lee, D. Liskovich, Y. Lu, Y. Mao, X. Martinet, T. Mihaylov, P. Mishra, I. Molybog, Y. Nie, A. Poulton, J. Reizenstein, R. Rungta, K. Saladi, A. Schelten, R. Silva, E. M. Smith, R. Subramanian, X. E. Tan, B. Tang, R. Taylor, A. Williams, J. X. Kuan, P. Xu, Z. Yan, I. Zarov, Y. Zhang, A. Fan, M. Kambadur, S. Narang, A. Rodriguez, R. Stojnic, S. Edunov, and T. Scialom, “Llama 2: Open foundation and fine-tuned chat models,” arXiv, 7 2023. [Online]. Available: https://arxiv.org/abs/2307.09288
  47. Mistral-AI-Team, “Au large | mistral ai | frontier ai in your hands,” 2024. [Online]. Available: https://mistral.ai/news/mistral-large/
  48. S. M. Bsharat, A. Myrzakhan, and Z. Shen, “Principled instructions are all you need for questioning llama-1/2, gpt-3.5/4,” arXiv, 12 2023. [Online]. Available: https://arxiv.org/abs/2312.16171
  49. M. Renze and E. Guven, “The benefits of a concise chain of thought on problem-solving in large language models,” arXiv, 1 2024. [Online]. Available: https://arxiv.org/abs/2401.05618v1
  50. ——, “The effect of sampling temperature on problem solving in large language models,” arXiv, 2 2024. [Online]. Available: https://arxiv.org/abs/2402.05201v1
  51. Q. McNemar, “Note on the sampling error of the difference between correlated proportions or percentages,” Psychometrika, vol. 12, pp. 153–157, 6 1947. [Online]. Available: https://doi.org/10.1007/BF02295996
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Matthew Renze (3 papers)
  2. Erhan Guven (7 papers)
Citations (15)
View on Semantic Scholar
Youtube Logo Streamline Icon: https://streamlinehq.com

YouTube