CoReaAgents: A Collaboration and Reasoning Framework Based on LLM-Powered Agents for Complex Reasoning Tasks
Source abstract
Abstract
As LLMs demonstrate remarkable reasoning capabilities, LLM-powered agents are seen as key to achieving AGI (Artificial General Intelligence) and are widely applied in various complex real-world scenarios. Nevertheless, existing studies still suffer from missing steps, deviated task execution and incorrect tool selection. This paper proposes CoReaAgents, a collaboration and reasoning framework based on LLM-powered agents, comprising the Plan Agent (as a precise task planner), the Tool Agent (as a proficient tool user) and the Reflect Agent (as an objective task evaluator). These agents simulate the social division of labor and synergistic cooperation to enable each agent to perform different specialized capabilities in order to solve complex tasks together. Through the above mechanism, the CoReaAgents framework has the skills of prospective thinking and flexible execution. To verify the capability of the CoReaAgents framework, this paper conducts extensive experiments on different complex tasks such as tool learning, math reasoning and multi-hop QA. The results show that the CoReaAgents framework outperforms various comparative methods in both quantity and quality.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Semantic Web and Ontologies · Multi-Agent Systems and Negotiation · Business Process Modeling and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China
Key Laboratory of Network Information System Technology (NIST), Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China
Key Laboratory of Target Cognition and Application Technology (TCAT), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China
School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100190, China
College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
Institute of Tracking and Telecommunications Technology, Beijing 100094, China
References (69)
Show source-provided references
1. Debates on the Nature of Artificial General Intelligence10.1126/science.ado7069 ↗
2. Human-Level Control through Deep Reinforcement Learning10.1038/nature14236 ↗
3. Durante, Z., Huang, Q., Wake, N., Gong, R., Park, J.S., Sarkar, B., Taori, R., Noda, Y., Terzopoulos, D., and Choi, Y. (2024). Agent AI: Surveying the Horizons of Multimodal Interaction. arXiv.
4. Heaven, W.D. (2024, June 01). Google DeepMind Wants to Define What Counts as Artificial General Intelligence, MIT Technology Review, Available online: https://www.technologyreview.com/2023/11/16/1083498.
5. Xu, J., Fei, H., Pan, L., Liu, Q., Lee, M.-L., and Hsu, W. (2024, January 11–16). Faithful Logical Reasoning via Symbolic Chain-of-Thought. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Bangkok, Thailand.10.18653/v1/2024.acl-long.720 ↗
6. Mastering the Game of Go with Deep Neural Networks and Tree Search10.1038/nature16961 ↗
7. Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. (2013). Playing Atari with Deep Reinforcement Learning. arXiv.
8. Liu, R., Yang, R., Jia, C., Zhang, G., Zhou, D., Dai, A.M., Yang, D., and Vosoughi, S. (2023). Training Socially Aligned Language Models in Simulated Human Society. arXiv.
9. Sumers, T.R., Yao, S., Narasimhan, K., and Griffiths, T.L. (2023). Cognitive Architectures for Language Agents. arXiv.
10. Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Wang, J., Zhang, C., Wang, Z., Yau, S.K.S., and Lin, Z. (2024, January 7–11). MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria.
11. Xie, J., Chen, Z., Zhang, R., Wan, X., and Li, G. (2024). Large Multimodal Agents: A Survey. arXiv.
12. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
13. Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T., Cao, Y., and Narasimhan, K. (2023). Tree of Thoughts: Deliberate Problem Solving with Large Language Models. Advances in Neural Information Processing Systems, MIT Press.
14. Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
15. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023, January 1–5). ReAct: Synergizing Reasoning and Acting in Language Models. Proceedings of the International Conference on Learning Representations (ICLR), Kigali, Rwanda.
16. Shen, W., Li, C., Chen, H., Yan, M., Quan, X., Chen, H., Zhang, J., and Huang, F. (2024, January 12–16). Small LLMs Are Weak Tool Learners: A Multi-LLM Agent. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Miami, FL, USA.10.18653/v1/2024.emnlp-main.929 ↗
17. Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., and Yao, S. (2023). Reflexion: Language Agents with Verbal Reinforcement Learning. Advances in Neural Information Processing Systems, MIT Press.
18. Wang, Z., Mao, S., Wu, W., Ge, T., Wei, F., and Ji, H. (2024, January 16–21). Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Mexico City, Mexico.10.18653/v1/2024.naacl-long.15 ↗
19. Camel: Communicative Agents for “Mind” Exploration of Large Language Model Society
20. Qiao, S., Zhang, N., Fang, R., Luo, Y., Zhou, W., Jiang, Y.E., Lv, C., and Chen, H. (2024, January 7–11). AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning. Proceedings of the ICLR 2024 Workshop on Large Language Model (LLM) Agents, Vienna, Austria.
21. Bo, X., Zhang, Z., Dai, Q., Feng, X., Wang, L., Li, R., Chen, X., and Wen, J.-R. (2024, January 9–15). Reflective Multi-Agent Collaboration Based on Large Language Models. Proceedings of the Thirty-Eighth Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada.
22. Yang, R., Song, L., Li, Y., Zhao, S., Ge, Y., Li, X., and Shan, Y. (2023). Gpt4tools: Teaching Large Language Model to Use Tools via Self-Instruction. Advances in Neural Information Processing Systems, MIT Press.
23. Gorilla: Large Language Model Connected with Massive APIs
24. Gou, Z., Shao, Z., Gong, Y., Shen, Y., Yang, Y., Huang, M., Duan, N., and Chen, W. (2023). Tora: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving. arXiv.
25. Song, Y., Xiong, W., Zhu, D., Wu, W., Qian, H., Song, M., Huang, H., Li, C., Wang, K., and Yao, R. (2023). RestGPT: Connecting Large Language Models with Real-World RESTful APIs. arXiv.
26. Schick, T., Dwivedi-Yu, J., Dessí, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L., Cancedda, N., and Scialom, T. (2023). Toolformer: Language Models Can Teach Themselves to Use Tools. Advances in Neural Information Processing Systems, MIT Press.
27. Lu, P., Peng, B., Cheng, H., Galley, M., Chang, K., Wu, Y.N., Zhu, S., and Gao, J. (2023). Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models. Advances in Neural Information Processing Systems, MIT Press.
28. Liu, X., Peng, Z., Yi, X., Xie, X., Xiang, L., Liu, Y., and Xu, D. (2024). ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph. arXiv.
29. Crowd Intelligence in AI 2.0 Era10.1631/FITEE.1601859 ↗
30. From LSAT: The Progress and Challenges of Complex Reasoning10.1109/TASLP.2022.3164218 ↗
31. Liu, J., Cui, L., Liu, H., Huang, D., Wang, Y., and Zhang, Y. (2021, January 7–15). LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20), California, CA, USA.10.24963/ijcai.2020/501 ↗
32. Talmor, A., Herzig, J., Lourie, N., and Berant, J. (2019, January 2–7). CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA.
33. Ornes, S. (Quanta Magazine, 2023). The Unpredictable Abilities Emerging from Large AI Models, Quanta Magazine.
34. Li, M., Zhao, Y., Yu, B., Song, F., Li, H., Yu, H., Li, Z., Huang, F., and Li, Y. (2023, January 6–10). API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore.10.18653/v1/2023.emnlp-main.187 ↗
35. Qu, C., Dai, S., Wei, X., Cai, H., Wang, S., Yin, D., Xu, J., and Wen, J.-R. (2025). Tool learning with large language models: A survey. Front. Comput. Sci., 19.10.1007/s11704-024-40678-2 ↗
36. Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., and Qian, B. (2024, January 7–11). ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs. Proceedings of the ICLR 2024, Vienna, Austria.
37. Patel, A., Bhattamishra, S., and Goyal, N. (2021, January 6–11). Are NLP Models Really Able to Solve Simple Math Word Problems?. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Mexico City, Mexico.10.18653/v1/2021.naacl-main.168 ↗
38. Cobbe, K., Kosaraju, V., Bavarian, M., Chen, M., Jun, H., Kaiser, L., Plappert, M., Tworek, J., Hilton, J., and Nakano, R. (2021). Training Verifiers to Solve Math Word Problems. arXiv.
39. Ling, W., Yogatama, D., Dyer, C., and Blunsom, P. (August, January 30). Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vancouver, BC, Canada.
40. Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., and Zhou, D. (2022). Self-Consistency Improves Chain of Thought Reasoning in Language Models. arXiv.
41. Zhang, W., Shen, Y., Wu, L., Peng, Q., Wang, J., Zhuang, Y., and Lu, W. (2024, January 11–16). Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Bangkok, Thailand.10.18653/v1/2024.acl-long.197 ↗
42. Yuan, S., Song, K., Chen, J., Tan, X., Shen, Y., Ren, K., Li, D., and Yang, D. (May, January 29). EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Albuquerque, NM, USA.
43. Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W., Salakhutdinov, R., and Manning, C.D. (November, January 31). HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.10.18653/v1/D18-1259 ↗
44. Knowledge Graphs: Opportunities and Challenges10.1007/s10462-023-10465-9 ↗
45. Ding, M., Zhou, C., Chen, Q., Yang, H., and Tang, J. (August, January 28). Cognitive Graph for Multi-Hop Reading Comprehension at Scale. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy.
46. Saxena, A., Tripathi, A., and Talukdar, P. (2020, January 5–10). Improving Multi-Hop Question Answering over Knowledge Graphs Using Knowledge Base Embeddings. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online.10.18653/v1/2020.acl-main.412 ↗
47. Wu, S., Yacub, Z., and Shasha, D. (2024). DietNerd: A Nutrition Question-Answering System That Summarizes and Evaluates Peer-Reviewed Scientific Articles. Appl. Sci., 14.10.3390/app14199021 ↗
48. Guan, J., Wu, W., Wen, Z., Xu, P., Wang, H., and Huang, M. (2024). AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback. arXiv.
49. Fang, Y., Thomas, S., and Zhu, X. (2024, January 21–22). HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation. Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024), Mexico City, Mexico.10.18653/v1/2024.trustnlp-1.12 ↗
50. Chen, R., Jiang, W., Qin, C., Rawal, I.S., Tan, C., Choi, D., Xiong, B., and Ai, B. (2024, January 12–16). LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environments. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Miami, FL, USA.10.18653/v1/2024.findings-emnlp.844 ↗
51. Zhao, W.X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., and Dong, Z. (2023). A Survey of Large Language Models. arXiv.
52. Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., and Metzler, D. (2022). Emergent Abilities of Large Language Models. arXiv.
53. Park, J.S., O’Brien, J., Cai, C.J., Morris, M.R., Liang, P., and Bernstein, M.S. (November, January 29). Generative Agents: Interactive Simulacra of Human Behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, San Francisco, CA, USA.
54. Graph of Thoughts: Solving Elaborate Problems with Large Language Models
55. Ling, C., Zhao, X., Lu, J., Deng, C., Zheng, C., Wang, J., Chowdhury, T., Li, Y., Cui, H., and Zhang, X. (2023). Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey. arXiv.
56. Tang, Q., Deng, Z., Lin, H., Han, X., Liang, Q., Cao, B., and Sun, L. (2023). ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases. arXiv.
57. Talebirad, Y., and Nadiri, A. (2023). Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents. arXiv.
58. Fu, Y., Peng, H., Khot, T., and Lapata, M. (2023, January 6–9). Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback. Proceedings of the CoRR 2023, Atlanta, GA, USA.
59. Qin, Y., Zhou, E., Liu, Q., Yin, Z., Sheng, L., Zhang, R., Qiao, Y., and Shao, J. (2024, January 16–22). MP5: A Multi-Modal Open-Ended Embodied System in Minecraft via Active Perception. Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.01543 ↗
60. Xu, Y., Wang, S., Li, P., Luo, F., Wang, X., Liu, W., and Liu, Y. (2023). Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf. arXiv.
61. Chan, C.-M., Chen, W., Su, Y., Yu, J., Xue, W., Zhang, S., Fu, J., and Liu, Z. (2024, January 7–11). ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria.
62. Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication
63. Wang, Z., Wang, Y., Liu, X., Ding, L., Zhang, M., Liu, J., and Zhang, M. (2025). AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration. arXiv.
64. Sainz, O., García-Ferrero, I., Agerri, R., de Lacalle, O.L., Rigau, G., and Agirre, E. (2024, January 7–11). GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction. Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024), Vienna, Austria.
65. Training Language Models to Follow Instructions with Human Feedback
66. Liu, Y., Peng, X., Zhang, Y., Cao, J., Zhang, X., Cheng, S., Wang, X., Yin, J., and Du, T. (2024). Tool-Planner: Dynamic Solution Tree Planning for Large Language Model with Tool Clustering. arXiv.
67. Hao, S., Liu, T., Wang, Z., and Hu, Z. (2023). ToolKengpt: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings. Advances in Neural Information Processing Systems, MIT Press.
68. Han, J., Buntine, W., and Shareghi, E. (2024, January 11–16). Towards Uncertainty-Aware Language Agent. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2024, Bangkok, Thailand.10.18653/v1/2024.findings-acl.398 ↗
69. Press, O., Zhang, M., Min, S., Schmidt, L., Smith, N., and Lewis, M. (2023, January 6–10). Measuring and Narrowing the Compositionality Gap in Language Models. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore.10.18653/v1/2023.findings-emnlp.378 ↗