請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93862完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳銘憲 | zh_TW |
| dc.contributor.advisor | Ming-Syan Chen | en |
| dc.contributor.author | 王順貴 | zh_TW |
| dc.contributor.author | Shun-Gui Wang | en |
| dc.date.accessioned | 2024-08-08T16:37:27Z | - |
| dc.date.available | 2024-08-09 | - |
| dc.date.copyright | 2024-08-08 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-03 | - |
| dc.identifier.citation | [1] M. Abdin, S. A. Jacobs, A. A. Awan, J. Aneja, A. Awadallah, H. Awadalla, N. Bach, A. Bahree, A. Bakhtiari, H. Behl, et al. Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219, 2024.
[2] J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023. [3] Anthropic. Introducing the next generation of claude. https://www.anthropic.com/news/claude-3-family, 2024. Accessed:18/7/2024. [4] M. Besta, N. Blach, A. Kubicek, R. Gerstenberger, L. Gianinazzi, J. Gajda, T. Lehmann, M. Podstawski, H. Niewiadomski, P. Nyczyk, and T. Hoefler. Graph of Thoughts: Solving Elaborate Problems with Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16):17682–17690, Mar 2024. [5] C. E. E. Center. The questions in the science portion of the general scholastic ability test. https://www.ceec.edu.tw/xmfile?xsmsid=0J052424829869345634, 2021. Accessed:18/7/2024. [6] Z. Chai, G. Wang, J. Su, T. Zhang, X. Huang, X. Wang, J. Xu, J. Yuan, H. Yang, F. Wu, and Y. Yang. An expert is worth one token: Synergizing multiple expert llms as generalist via expert token routing. CoRR, abs/2403.16854, 2024. [7] C. Chan, W. Chen, Y. Su, J. Yu, W. Xue, S. Zhang, J. Fu, and Z. Liu. Chateval: Towards better llm-based evaluators through multi-agent debate. CoRR, abs/2308.07201, 2023. [8] L. Chen, M. Zaharia, and J. Zou. Frugalgpt: How to use large language models while reducing cost and improving performance. arXiv preprint arXiv:2305.05176, 2023. [9] W. Chen and Z. Li. Octopus v4: Graph of language models, 2024. [10] W. Chen, Y. Su, J. Zuo, C. Yang, C. Yuan, C.-M. Chan, H. Yu, Y. Lu, Y.-H. Hung, C. Qian, Y. Qin, X. Cong, R. Xie, Z. Liu, M. Sun, and J. Zhou. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors. In The Twelfth International Conference on Learning Representations, 2024. [11] Y. Chen, J. Arkin, Y. Zhang, N. Roy, and C. Fan. Scalable multi-robot collaboration with large language models: Centralized or decentralized systems? arXiv preprint arXiv:2309.15943, 2023. [12] Z. Chen, K. Zhou, B. Zhang, Z. Gong, X. Zhao, and J. Wen. Chatcot: Tool-augmented chain-of-thought reasoning on chat-based large language models. In H. Bouamor, J. Pino, and K. Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 14777–14790. Association for Computational Linguistics, 2023. [13] A. Cloud. Qwen1.5. https://huggingface.co/collections/Qwen/qwen15-65c0a2f577b1ecb76d786524, 2024. Accessed:18/7/2024. [14] G. Dagan, F. Keller, and A. Lascarides. Dynamic planning with a LLM. CoRR, abs/2308.06391, 2023. [15] D. Ding, A. Mallick, C. Wang, R. Sim, S. Mukherjee, V. Rühle, L. V. S. Lakshmanan, and A. H. Awadallah. Hybrid LLM: Cost-efficient and quality-aware query routing. In The Twelfth International Conference on Learning Representations, 2024. [16] Y. Du, S. Li, A. Torralba, J. B. Tenenbaum, and I. Mordatch. Improving factuality and reasoning in language models through multiagent debate. CoRR, abs/2305.14325, 2023. [17] Y. Fu, H. Peng, T. Khot, and M. Lapata. Improving language model negotiation with self-play and in-context learning from AI feedback. CoRR, abs/2305.10142, 2023. [18] S. Hamilton. Blind judgement: Agent-based supreme court modelling with GPT. CoRR, abs/2301.05327, 2023. [19] R. Hao, L. Hu, W. Qi, Q. Wu, Y. Zhang, and L. Nie. Chatllm network: More brains, more intelligence. CoRR, abs/2304.12998, 2023. [20] S. Hao, Y. Gu, H. Ma, J. J. Hong, Z. Wang, D. Z. Wang, and Z. Hu. Reasoning with language model is planning with world model. In H. Bouamor, J. Pino, and K. Bali, editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 8154–8173. Association for Computational Linguistics, 2023. [21] D. Hendrycks, C. Burns, S. Basart, A. Zou, M. Mazeika, D. Song, and J. Steinhardt. Measuring massive multitask language understanding. In International Conference on Learning Representations, 2021. [22] S. Hong, M. Zhuge, J. Chen, X. Zheng, Y. Cheng, J. Wang, C. Zhang, Z. Wang, S. K. S. Yau, Z. Lin, L. Zhou, C. Ran, L. Xiao, C. Wu, and J. Schmidhuber. MetaGPT: Meta programming for a multi-agent collaborative framework. In The Twelfth International Conference on Learning Representations, 2024. [23] W. Huang, P. Abbeel, D. Pathak, and I. Mordatch. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In K. Chaudhuri, S. Jegelka, L. Song, C. Szepesvári, G. Niu, and S. Sabato, editors, International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings of Machine Learning Research, pages 9118–9147. PMLR, 2022. [24] W. Huang, F. Xia, T. Xiao, H. Chan, J. Liang, P. Florence, A. Zeng, J. Tompson, I. Mordatch, Y. Chebotar, P. Sermanet, T. Jackson, N. Brown, L. Luu, S. Levine, K. Hausman, and B. Ichter. Inner monologue: Embodied reasoning through planning with language models. In K. Liu, D. Kulic, and J. Ichnowski, editors, Conference on Robot Learning, CoRL 2022, 14-18 December 2022, Auckland, New Zealand, volume 205 of Proceedings of Machine Learning Research, pages 1769–1782. PMLR, 2022. [25] A. Q. Jiang, A. Sablayrolles, A. Roux, A. Mensch, B. Savary, C. Bamford, D. S. Chaplot, D. d. l. Casas, E. B. Hanna, F. Bressand, et al. Mixtral of experts. arXiv preprint arXiv:2401.04088, 2024. [26] D. Jiang, X. Ren, and B. Y. Lin. Llm-blender: Ensembling large language models with pairwise comparison and generative fusion. In Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics (ACL 2023), 2023. [27] J. Kaplan, S. McCandlish, T. Henighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020. [28] T. Khot, H. Trivedi, M. Finlayson, Y. Fu, K. Richardson, P. Clark, and A. Sabharwal. Decomposed prompting: A modular approach for solving complex tasks. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023. [29] T. Kojima, S. S. Gu, M. Reid, Y. Matsuo, and Y. Iwasawa. Large language models are zero-shot reasoners. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, 2022. [30] G. Li, H. A. A. K. Hammoud, H. Itani, D. Khizbullin, and B. Ghanem. CAMEL: Communicative agents for ”mind” exploration of large language model society. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. [31] T. Liang, Z. He, W. Jiao, X. Wang, Y. Wang, R. Wang, Y. Yang, Z. Tu, and S. Shi. Encouraging divergent thinking in large language models through multi-agent debate. CoRR, abs/2305.19118, 2023. [32] B. Liu, Y. Jiang, X. Zhang, Q. Liu, S. Zhang, J. Biswas, and P. Stone. LLM+P: empowering large language models with optimal planning proficiency. CoRR, abs/2304.11477, 2023. [33] R. Liu, R. Yang, C. Jia, G. Zhang, D. Yang, and S. Vosoughi. Training socially aligned language models on simulated social interactions. In The Twelfth International Conference on Learning Representations, 2024. [34] K. Lu, H. Yuan, R. Lin, J. Lin, Z. Yuan, C. Zhou, and J. Zhou. Routing to the expert: Efficient reward-guided ensemble of large language models. In K. Duh, H. Gomez, and S. Bethard, editors, Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1964–1974, Mexico City, Mexico, June 2024. Association for Computational Linguistics. [35] A. Madaan, P. Aggarwal, A. Anand, S. P. Potharaju, S. Mishra, P. Zhou, A. Gupta, D. Rajagopal, K. Kappaganthu, Y. Yang, S. Upadhyay, Mausam, and M. Faruqui. Automix: Automatically mixing language models, 2023. [36] 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. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023. [37] Z. Mandi, S. Jain, and S. Song. Roco: Dialectic multi-robot collaboration with large language models. CoRR, abs/2307.04738, 2023. [38] MetaAI. Introducing meta llama 3: The most capable openly available llm to date. https://ai.meta.com/blog/meta-llama-3/, 2024. Accessed:18/7/2024. [39] N. Miao, Y. W. Teh, and T. Rainforth. Selfcheck: Using llms to zero-shot check their own step-by-step reasoning. CoRR, abs/2308.00436, 2023. [40] Ollama. a. https://www.ollama.com/, 2023. Accessed:18/7/2024. [41] OpenAI. gpt-3.5-turbo. https://platform.openai.com/docs/models/gpt-3-5-turbo, 2021. Accessed: 18/7/2024. [42] C. Qian, X. Cong, C. Yang, W. Chen, Y. Su, J. Xu, Z. Liu, and M. Sun. Communicative agents for software development. arXiv preprint arXiv:2307.07924, 2023. [43] S. S. Raman, V. Cohen, E. Rosen, I. Idrees, D. Paulius, and S. Tellex. Planning with large language models via corrective re-prompting. CoRR, abs/2211.09935, 2022. [44] K. Rana, J. Haviland, S. Garg, J. Abou-Chakra, I. D. Reid, and N. Sünderhauf. Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning. In J. Tan, M. Toussaint, and K. Darvish, editors, Conference on Robot Learning, CoRL 2023, 6-9 November 2023, Atlanta, GA, USA, volume 229 of Proceedings of Machine Learning Research, pages 23–72. PMLR, 2023. [45] Y. Shen, K. Song, X. Tan, D. Li, W. Lu, and Y. Zhuang. Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. In Advances in Neural Information Processing Systems, 2023. [46] J. Shi, J. Zhao, Y. Wang, X. Wu, J. Li, and L. He. CGMI: configurable general multi-agent interaction framework. CoRR, abs/2308.12503, 2023. [47] N. Shinn, B. Labash, and A. Gopinath. Reflexion: an autonomous agent with dynamic memory and self-reflection. CoRR, abs/2303.11366, 2023. [48] T. Shnitzer, A. Ou, M. Silva, K. Soule, Y. Sun, J. Solomon, N. Thompson, and M. Yurochkin. Large language model routing with benchmark datasets, 2023. [49] K. Singhal, T. Tu, J. Gottweis, R. Sayres, E. Wulczyn, L. Hou, K. Clark, S. Pfohl, H. Cole-Lewis, D. Neal, et al. Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2305.09617, 2023. [50] C. H. Song, B. M. Sadler, J. Wu, W. Chao, C. Washington, and Y. Su. Llm-planner: Few-shot grounded planning for embodied agents with large language models. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, pages 2986–2997. IEEE, 2023. [51] Y. Talebirad and A. Nadiri. Multi-agent collaboration: Harnessing the power of intelligent llm agents. arXiv preprint arXiv:2306.03314, 2023. [52] G. Team, R. Anil, S. Borgeaud, Y. Wu, J.-B. Alayrac, J. Yu, R. Soricut, J. Schalkwyk, A. M. Dai, A. Hauth, et al. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805, 2023. [53] G. Wang, Y. Xie, Y. Jiang, A. Mandlekar, C. Xiao, Y. Zhu, L. Fan, and A. Anandkumar. Voyager: An open-ended embodied agent with large language models. CoRR, abs/2305.16291, 2023. [54] L. Wang, C. Ma, X. Feng, Z. Zhang, H. Yang, J. Zhang, Z. Chen, J. Tang, X. Chen, Y. Lin, W. X. Zhao, Z. Wei, and J. Wen. A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6), Mar. 2024. [55] X. Wang, J. Wei, D. Schuurmans, Q. V. Le, E. H. Chi, S. Narang, A. Chowdhery, and D. Zhou. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023. [56] Z. Wang, S. Cai, G. Chen, A. Liu, X. Ma, and Y. Liang. Describe, explain, plan and select: Interactive planning with LLMs enables open-world multi-task agents. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. [57] Z. Wang, S. Mao, W. Wu, T. Ge, F. Wei, and H. Ji. Unleashing the emergent cognitive synergy in large language models: A task-solving agent through multi-persona selfcollaboration. arXiv preprint arXiv:2307.05300, 2023. [58] J. Wei, X. Wang, D. Schuurmans, M. Bosma, B. Ichter, F. Xia, E. H. Chi, Q. V. Le, and D. Zhou. Chain-of-thought prompting elicits reasoning in large language models. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, 2022. [59] Weyaxi. Einstein-v6.1-llama3-8b. https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B, 2024. Accessed:18/7/2024. [60] Q. Wu, G. Bansal, J. Zhang, Y. Wu, S. Zhang, E. Zhu, B. Li, L. Jiang, X. Zhang, and C. Wang. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155, 2023. [61] S. Wu, O. Irsoy, S. Lu, V. Dabravolski, M. Dredze, S. Gehrmann, P. Kambadur, D. Rosenberg, and G. Mann. Bloomberggpt: A large language model for finance. arXiv preprint arXiv:2303.17564, 2023. [62] T. Wu, M. Terry, and C. J. Cai. AI chains: Transparent and controllable human-ai interaction by chaining large language model prompts. In S. D. J. Barbosa, C. Lampe, C. Appert, D. A. Shamma, S. M. Drucker, J. R. Williamson, and K. Yatani, editors, CHI ’22: CHI Conference on Human Factors in Computing Systems, New Orleans, LA, USA, 29 April 2022 - 5 May 2022, pages 385:1–385:22. ACM, 2022. [63] Z. Xi, W. Chen, X. Guo, W. He, Y. Ding, B. Hong, M. Zhang, J. Wang, S. Jin, E. Zhou, et al. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864, 2023. [64] K. Xiong, X. Ding, Y. Cao, T. Liu, and B. Qin. Examining the inter-consistency of large language models: An in-depth analysis via debate. CoRR, abs/2305.11595, 2023. [65] B. Xu, Z. Peng, B. Lei, S. Mukherjee, Y. Liu, and D. Xu. Rewoo: Decoupling reasoning from observations for efficient augmented language models. CoRR, abs/2305.18323, 2023. [66] S. Yao, D. Yu, J. Zhao, I. Shafran, T. Griffiths, Y. Cao, and K. Narasimhan. Tree of thoughts: Deliberate problem solving with large language models. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023. [67] S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. R. Narasimhan, and Y. Cao. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023. [68] A. Young, B. Chen, C. Li, C. Huang, G. Zhang, G. Zhang, H. Li, J. Zhu, J. Chen, J. Chang, et al. Yi: Open foundation models by 01. ai. arXiv preprint arXiv:2403.04652, 2024. [69] M. Yue, J. Zhao, M. Zhang, L. Du, and Z. Yao. Large language model cascades with mixture of thought representations for cost-efficient reasoning. In The Twelfth International Conference on Learning Representations, 2024. [70] C. Zhang, K. Yang, S. Hu, Z. Wang, G. Li, Y. Sun, C. Zhang, Z. Zhang, A. Liu, S. Zhu, X. Chang, J. Zhang, F. Yin, Y. Liang, and Y. Yang. Proagent: Building proactive cooperative agents with large language models. In M. J. Wooldridge, J. G. Dy, and S. Natarajan, editors, Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pages 17591–17599. AAAI Press, 2024. [71] H. Zhang, W. Du, J. Shan, Q. Zhou, Y. Du, J. B. Tenenbaum, T. Shu, and C. Gan. Building cooperative embodied agents modularly with large language models. In The Twelfth International Conference on Learning Representations, 2024. [72] X. Zhao, M. Li, C. Weber, M. B. Hafez, and S. Wermter. Chat with the environment: Interactive multimodal perception using large language models. In IROS, pages 3590–3596, 2023. [73] D. Zhou, N. Schärli, L. Hou, J. Wei, N. Scales, X. Wang, D. Schuurmans, C. Cui, O. Bousquet, Q. V. Le, and E. H. Chi. Least-to-most prompting enables complex reasoning in large language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93862 | - |
| dc.description.abstract | 大型語言模型如GPT-4 在各種任務中展現了卓越的能力。然而，沒有任何單一的大型語言模型能夠最佳地處理所有類型的任務和應用。為了應對這一限制，必須結合各種特定領域大型語言模型的優勢，利用它們的獨特能力來克服單個模型的約束。鑑於通過付費API 服務訪問最強大的大型語言模型相關費用高昂，一種具有成本效益的方法是根據任務難度整合不同規模的大型語言模型。路由的範圍可以擴展到包含由多個領域或不同難度級別的子任務組成的更複雜的任務。在這種情況下，將單個任務分配給一個模型不足以完成任務。這些複雜的任務必須按任務領域或難度進行分解，並將子任務進一步分配給不同的大型語言模型。我們提出了一種基於大型語言模型的新方法，即任務專家協作（CoTE），該方法利用大型語言模型的推理能力和豐富知識來進行任務分解和專家分配。CoTE 將每個大型語言模型的獨特特徵，包括其專業領域和模型規模，整合到提示中。在簡單任務上的廣泛實驗比較中，CoTE 表現出卓越的路由準確性。在複雜任務實驗中，CoTE 在多領域MMLU 任務上實現了95.00% 的路由準確性和17.00% 的總體準確性提升，在多難度MMLU 任務上實現了79.60% 的路由準確性並顯著降低了成本，這突顯了其在任務分解和專家分配方面的有效性。 | zh_TW |
| dc.description.abstract | Large Language Models (LLMs) like GPT-4 have shown remarkable proficiency across various tasks. However, no single LLM can optimally manage all types of tasks and applications. To address this limitation, it is essential to combine the strengths of various domain-specific LLMs, leveraging their unique capabilities to overcome the constraints of individual models. Given the high costs associated with accessing the most powerful LLMs via paid API services, a cost-effective approach involves incorporating LLMs of different sizes based on task difficulty. The scope of routing can be extended to encompass more complex tasks that consist of sub-tasks spanning multiple domains or varying levels of difficulty. In such cases, assigning a single task to one model is insufficient to achieve task completion. These complex tasks must be decomposed by task domains or difficulty, with sub-tasks further assigned to different LLMs. We propose a novel LLM-based method, Collaboration-of-Task-Expert (CoTE), which uses the reasoning ability and vast knowledge of LLMs for task decomposition and expert assignment. CoTE integrates the unique characteristics of each LLM, including their areas of expertise and model size, into prompts. Extensive experimental comparisons with previous routing methods on simple tasks demonstrate CoTE ’s superior routing accuracy. In complex task experiments, CoTE achieves a 95.00% routing accuracy and a 17.00% overall accuracy improvement on multi-domain MMLU tasks, as well as a 79.60% routing accuracy and a significant cost reduction on multi-difficulty MMLU tasks, highlighting its effectiveness in task decomposition and expert assignment. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-08-08T16:37:26Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-08-08T16:37:27Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Contents
Page 口試委員會審定書 i Acknowledgements ii 摘要 iii Abstract iv Contents vi List of Figures viii List of Tables ix Chapter 1 Introduction 1 Chapter 2 Related Work 6 2.1 LLM Reasoning and Planning . . . . . . . . . . . . . . . . . . . . . 6 2.2 LLM-based Multi-Agent Systems . . . . . . . . . . . . . . . . . . . 7 2.3 Multi-LLM Routing . . . . . . . . . . . . . . . . . . . . . . . . . . 9 Chapter 3 Problem Formulation 11 Chapter 4 Methodology 13 4.1 Collaboration-of-Task-Expert . . . . . . . . . . . . . . . . . . . . . 14 4.1.1 Preparation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.1.2 Decomposition and Assignment . . . . . . . . . . . . . . . . . . . 14 4.1.3 Sub-Tasks Solving . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.2 Prompt Construction . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.2.1 Task Description . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.2.2 Expert Library Information . . . . . . . . . . . . . . . . . . . . . . 15 Chapter 5 Experiments 17 5.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 5.1.1 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 5.1.1.1 Simple and Complex Tasks . . . . . . . . . . . . . . . 17 5.1.1.2 Multi-Domain Complex Tasks . . . . . . . . . . . . . 18 5.1.1.3 Multi-Difficulty Complex Tasks . . . . . . . . . . . . 18 5.1.2 Baselines . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 5.1.3 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . 19 5.1.4 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 5.2 Main Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 5.2.1 Expert Routing Accuracy . . . . . . . . . . . . . . . . . . . . . . . 20 5.2.2 Analysis on Multi-Agent System . . . . . . . . . . . . . . . . . . . 22 5.2.3 Routing Accuracy in Zero-Shot and Few-Shot . . . . . . . . . . . . 23 Chapter 6 Conclusion 24 References 25 | - |
| dc.language.iso | en | - |
| dc.subject | 多智能體系統 | zh_TW |
| dc.subject | 大型語言模型 | zh_TW |
| dc.subject | 查詢路由 | zh_TW |
| dc.subject | Query Routing | en |
| dc.subject | Large Language Models | en |
| dc.subject | Multi-Agent System | en |
| dc.title | 任務專家協作：多智能體系統的任務分解與專家分配 | zh_TW |
| dc.title | Collaboration-of-Task-Expert: Task Decomposition and Expert Assignment on Multi-Agent System | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 吳齊人;賴冠廷;葉彌妍 | zh_TW |
| dc.contributor.oralexamcommittee | Chi-Jen Wu;Kuan-Ting Lai;Mi-Yen Yeh | en |
| dc.subject.keyword | 大型語言模型,查詢路由,多智能體系統, | zh_TW |
| dc.subject.keyword | Large Language Models,Query Routing,Multi-Agent System, | en |
| dc.relation.page | 36 | - |
| dc.identifier.doi | 10.6342/NTU202402603 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2024-08-07 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 電機工程學系 | - |
| dc.date.embargo-lift | 2027-08-03 | - |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 未授權公開取用 | 1.37 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。