A Survey on the Optimization of Large Language Model-based Agents
Published version of a preprint
The DOI matches its Crossref record; 58 of the 58 references it cites were found in a registry or an index.
Abstract
With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks. However, current work typically relies on prompt design or fine-tuning strategies applied to vanilla LLMs, which often leads to limited effectiveness in complex agent-related environments. Although numerous recent studies have explored various strategies to optimize LLM-based agents for complex agent tasks, a systematic review summarizing and comparing these methods from a holistic perspective remains lacking. In this survey, we provide a comprehensive review of LLM-based agent optimization approaches, categorizing them into parameter-driven and parameter-free methods. We first focus on parameter-driven optimization, covering fine-tuning-based optimization, reinforcement learning-based optimization, and hybrid strategies, analyzing key aspects such as trajectory data construction, reward function design, and optimization algorithms. Additionally, we briefly discuss parameter-free strategies that optimize agent behavior through prompt engineering and external knowledge retrieval. Finally, we summarize the evaluation for agents, review key applications of LLM-based agents, and discuss the major challenges and promising future directions. A curated collection of the surveyed works is provided at https://github.com/YoungDubbyDu/LLM-Agent-Optimization.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · cited 1×
“Optimizing LLM-based agents requires a broader understanding of dynamic environments and agent behaviors, which needs to design specialized techniques that go beyond traditional LLM fine-tuning and prompt engineering methods.”
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083 · cited 1×
“Moreover, some datasets often include interactions generated by multi-agent systems or refined by LLMs, which can introduce cognitive biases from the LLMs, potentially amplifying or creating new biases based on prior model behavior.”
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W., Salakhutdinov, R., & Manning, C. D. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1259 · Cited by 1,804 · cited 1×
“Specifically, iVideoGPT supports interactive video-based reasoning, AutoRT automates multi-robot coordination for real-world data collection, and EMMA transfers LLM expertise across modalities, enabling quick adaptation to new visual tasks.”
Expel: LLM agents are experiential learners
Zhao, A., Huang, D., Xu, Q., Lin, M., Liu, Y.-J., & Huang, G. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29936 · Cited by 1,451
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
Liang, T., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., Yang, Y., Shi, S., & Tu, Z. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.992 · Cited by 1,062
The Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972 · cited 2×
“Unlike other surveys [64, 169, 210] that categorize methods based on agent structure or architecture, we categorize the methods based on the strategies and techniques employed to optimize the agent’s behavior, including experience-based optimization, feedback-based optimization, tool-based…”
The rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970
TruthfulQA: Measuring How Models Mimic Human Falsehoods
Lin, S., Hilton, J., & Evans, O. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.229 · Cited by 904 · cited 1×
“Specifically, iVideoGPT supports interactive video-based reasoning, AutoRT automates multi-robot coordination for real-world data collection, and EMMA transfers LLM expertise across modalities, enabling quick adaptation to new visual tasks.”
TruthfulQA: Measuring How Models Mimic Human Falsehoods
Lin, S., Hilton, J., & Evans, O. (2021) · arXiv · doi:10.48550/arxiv.2109.07958 · Cited by 899 · cited 1×
“Specifically, iVideoGPT supports interactive video-based reasoning, AutoRT automates multi-robot coordination for real-world data collection, and EMMA transfers LLM expertise across modalities, enabling quick adaptation to new visual tasks.”
P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks
Liu, X., Ji, K., Fu, Y., Tam, W., Du, Z., Yang, Z., & Tang, J. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/2022.acl-short.8 · Cited by 810 · cited 1×
“Policy-based methods , including Policy Gradient [48, 124], directly optimize the agent’s policy by adjusting parameters based on reward gradients.”
Research works printed but not linked: 171
- Michael Ahn Debidatta Dwibedi Chelsea Finn Montse Gonzalez Arenas Keerthana Gopalakrishnan Karol Hausman Brian Ichter Alex Irpan Nikhil Joshi Ryan Julian et al. 2024. Autort: Embodied foundation models for large scale orchestration of robotic agents. arXiv:2401.12963. Retrieved from https://arxiv.org/abs/2401.12963 · arXiv
- Renat Aksitov Sobhan Miryoosefi Zonglin Li Daliang Li Sheila Babayan Kavya Kopparapu Zachary Fisher Ruiqi Guo Sushant Prakash Pranesh Srinivasan et al. 2023. Rest meets react: Self-improvement for multi-step reasoning llm agent. arXiv:2312.10003. Retrieved from https://arxiv.org/abs/2312.10003 · arXiv
- Siyu An Qin Li Junru Lu Di Yin and Xing Sun. 2024. FinVerse: An autonomous agent system for versatile financial analysis. arXiv:2406.06379. Retrieved from https://arxiv.org/abs/2406.06379 · arXiv
- 10.1039/D4DD00252K · DOI
- 10.1109/ICCV.2015.279 · DOI · Paper page
- Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-RAG: Learning to retrieve, generate, and critique through self-reflection. In Proceedings of the 12th International Conference on Learning Representations.
- Zhijie Bao Wei Chen Shengze Xiao Kuang Ren Jiaao Wu Cheng Zhong Jiajie Peng Xuanjing Huang and Zhongyu Wei. 2023. Disc-medllm: Bridging general large language models and real-world medical consultation. arXiv:2308.14346. Retrieved from https://arxiv.org/abs/2308.14346 · arXiv
- Xiaohe Bo, Zeyu Zhang, Quanyu Dai, Xueyang Feng, Lei Wang, Rui Li, Xu Chen, and Ji-Rong Wen. 2025. Reflective multi-agent collaboration based on large language models. Advances in Neural Information Processing Systems 37 (2025), 138595–138631.
- Anthony Brohan, Yevgen Chebotar, Chelsea Finn, Karol Hausman, Alexander Herzog, Daniel Ho, Julian Ibarz, Alex Irpan, Eric Jang, Ryan Julian, et al. 2023. Do as i can, not as i say: Grounding language in robotic affordances. In Proceedings of the Conference on Robot Learning. PMLR, 287–318.
- 10.3390/app11114948 · DOI · Paper page
- Mert Cemri Melissa Z. Pan Shuyi Yang Lakshya A. Agrawal Bhavya Chopra Rishabh Tiwari Kurt Keutzer Aditya Parameswaran Dan Klein Kannan Ramchandran et al. 2025. Why do multi-agent llm systems fail? arXiv:2503.13657. Retrieved from https://arxiv.org/abs/2503.13657 · arXiv
- Jun Shern Chan Neil Chowdhury Oliver Jaffe James Aung Dane Sherburn Evan Mays Giulio Starace Kevin Liu Leon Maksin Tejal Patwardhan et al. 2024. Mle-bench: Evaluating machine learning agents on machine learning engineering. arXiv:2410.07095. Retrieved from https://arxiv.org/abs/2410.07095 · arXiv
- Junying Chen Zhenyang Cai Ke Ji Xidong Wang Wanlong Liu Rongsheng Wang Jianye Hou and Benyou Wang. 2024. Huatuogpt-o1 towards medical complex reasoning with llms. arXiv:2412.18925. Retrieved from https://arxiv.org/abs/2412.18925 · arXiv
- Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde De Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et al. 2021. Evaluating large language models trained on code. arXiv:2107.03374. Retrieved from https://arxiv.org/abs/2107.03374 · arXiv
- Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, et al. 2024. AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors. In Proceedings of the ICLR.
- Weize Chen Jiarui Yuan Chen Qian Cheng Yang Zhiyuan Liu and Maosong Sun. 2024. Optima: Optimizing effectiveness and efficiency for llm-based multi-agent system. arXiv:2410.08115. Retrieved from https://arxiv.org/abs/2410.08115 · arXiv
- Zhixun Chen Ming Li Yuxuan Huang Yali Du Meng Fang and Tianyi Zhou. 2025. ATLaS: Agent tuning via learning critical steps. arXiv:2503.02197. Retrieved from https://arxiv.org/abs/2503.02197 · DOI
- Zehui Chen Kuikun Liu Qiuchen Wang Wenwei Zhang Jiangning Liu Dahua Lin Kai Chen and Feng Zhao. 2024. Agent-FLAN: Designing data and methods of effective agent tuning for large language models. arXiv:2403.12881. Retrieved from https://arxiv.org/abs/2403.12881 · DOI
- Peter Clark Isaac Cowhey Oren Etzioni Tushar Khot Ashish Sabharwal Carissa Schoenick and Oyvind Tafjord. 2018. Think you have solved question answering? try arc the ai2 reasoning challenge. arXiv:1803.05457. Retrieved from https://arxiv.org/abs/1803.05457 · arXiv
- 10.1146/annurev-statistics-031219-041220 · DOI · Paper page
- Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et al. 2021. Training verifiers to solve math word problems. arXiv:2110.14168. Retrieved from https://arxiv.org/abs/2110.14168 · arXiv
- Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2023. Mind2web: Towards a generalist agent for the web. Advances in Neural Information Processing Systems 36 (2023), 28091–28114.
- Zhirui Deng Zhicheng Dou Yutao Zhu Ji-Rong Wen Ruibin Xiong Mang Wang and Weipeng Chen. 2024. From novice to expert: LLM agent policy optimization via step-wise reinforcement learning. arXiv:2411.03817. Retrieved from https://arxiv.org/abs/2411.03817 · arXiv
- Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems 36 (2023), 10088–10115.
- 10.1109/SC41406.2024.00013 · DOI
- Zi-Yi Dou, Cheng-Fu Yang, Xueqing Wu, Kai-Wei Chang, and Nanyun Peng. 2024. Re-rest: Reflection-reinforced self-training for language agents. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 15394–15411.
- Damien Ernst and Arthur Louette. 2024. Introduction to reinforcement learning. Feuerriegel, S., Hartmann, J., Janiesch, C., and Zschech, P (2024), 111–126.
- Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, and Qing Li. 2024. Videoagent: A memory-augmented multimodal agent for video understanding. In Proceedings of the European Conference on Computer Vision. Springer, 75–92.
- Zhihao Fan, Lai Wei, Jialong Tang, Wei Chen, Wang Siyuan, Zhongyu Wei, and Fei Huang. 2025. AI hospital: Benchmarking large language models in a multi-agent medical interaction simulator. In Proceedings of the 31st International Conference on Computational Linguistics. 10183–10213.
- 10.1145/3677052.3698688 · DOI
- Peiyuan Feng, Yichen He, Guanhua Huang, Yuan Lin, Hanchong Zhang, Yuchen Zhang, and Hang Li. 2024. AGILE: A novel reinforcement learning framework of LLM agents. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems.
- Xidong Feng Ziyu Wan Haotian Fu Bo Liu Mengyue Yang Girish A. Koushik Zhiyuan Hu Ying Wen and Jun Wang. 2024. Natural language reinforcement learning. arXiv:2411.14251. Retrieved from https://arxiv.org/abs/2411.14251 · arXiv
- Dayuan Fu, Biqing Qi, Yihuai Gao, Che Jiang, Guanting Dong, and Bowen Zhou. 2024. MSI-Agent: Incorporating multi-scale insight into embodied agents for superior planning and decision-making. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 643–659.
- Yao Fu, Dong-Ki Kim, Jaekyeom Kim, Sungryull Sohn, Lajanugen Logeswaran, Kyunghoon Bae, and Honglak Lee. 2024. Autoguide: Automated generation and selection of context-aware guidelines for large language model agents. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems.
- Shen Gao Yuntao Wen Minghang Zhu Jianing Wei Yuhan Cheng Qunzi Zhang and Shuo Shang. 2024. Simulating financial market via large language model based agents. arXiv:2406.19966. Retrieved from https://arxiv.org/abs/2406.19966 · arXiv
- Alireza Ghafarollahi and Markus J. Buehler. 2024. ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning. Digital Discovery 3, 7 (2024), 1389–1409. · DOI · Paper page
- Dibya Ghosh, Marlos C. Machado, and Nicolas Le Roux. 2020. An operator view of policy gradient methods. Advances in Neural Information Processing Systems 33 (2020), 3397–3406.
- Zhibin Gou, Zhihong Shao, Yeyun Gong, yelong shen, Yujiu Yang, Minlie Huang, Nan Duan, and Weizhu Chen. 2024. ToRA: A tool-integrated reasoning agent for mathematical problem solving. In Proceedings of the 12th International Conference on Learning Representations.
- Jian Guan, Wei Wu, zujie wen, Peng Xu, Hongning Wang, and Minlie Huang. 2024. AMOR: A recipe for building adaptable modular knowledge agents through process feedback. In Proceedings of the Advances in Neural Information Processing Systems. 126118–126148.
- Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv:2501.12948. Retrieved from https://arxiv.org/abs/2501.12948 · arXiv
- Priyanshu Gupta, Shashank Kirtania, Ananya Singha, Sumit Gulwani, Arjun Radhakrishna, Gustavo Soares, and Sherry Shi. 2024. MetaReflection: Learning instructions for language agents using past reflections. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 8369–8385. · DOI
- Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring massive multitask language understanding. Proceedings of the International Conference on Learning Representations (2021).
- Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring mathematical problem solving with the MATH dataset. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks.
- Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al. 2024. MetaGPT: Meta programming for a multi-agent collaborative framework. In Proceedings of the ICLR.
- Yining Hong, Zishuo Zheng, Peihao Chen, Yian Wang, Junyan Li, and Chuang Gan. 2024. Multiply: A multisensory object-centric embodied large language model in 3d world. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 26406–26416.
- Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In Proceedings of the International Conference on Learning Representations.
- Yusong Hu Runmin Ma Yue Fan Jinxin Shi Zongsheng Cao Yuhao Zhou Jiakang Yuan Xiangchao Yan Wenlong Zhang Lei Bai et al. 2025. FlowSearch: Advancing deep research with dynamic structured knowledge flow. arXiv:2510.08521. Retrieved from https://arxiv.org/abs/2510.08521 · arXiv
- Kaixuan Huang Yuanhao Qu Henry Cousins William A Johnson Di Yin Mihir Shah Denny Zhou Russ Altman Mengdi Wang and Le Cong. 2024. Crispr-gpt: An llm agent for automated design of gene-editing experiments. arXiv:2404.18021. Retrieved from https://arxiv.org/abs/2404.18021 · arXiv
- Xiang Huang, Sitao Cheng, Shanshan Huang, Jiayu Shen, Yong Xu, Chaoyun Zhang, and Yuzhong Qu. 2024. QueryAgent: A reliable and efficient reasoning framework with environmental feedback based self-correction. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 5014–5035. · DOI
- Xu Huang Weiwen Liu Xiaolong Chen Xingmei Wang Hao Wang Defu Lian Yasheng Wang Ruiming Tang and Enhong Chen. 2024. Understanding the planning of LLM agents: A survey. arXiv:2402.02716. Retrieved from https://arxiv.org/abs/2402.02716 · arXiv
- Haolin Jin Linghan Huang Haipeng Cai Jun Yan Bo Li and Huaming Chen. 2024. From llms to llm-based agents for software engineering: A survey of current challenges and future. arXiv:2408.02479. Retrieved from https://arxiv.org/abs/2408.02479 · arXiv
- Qiao Jin Zhizheng Wang Yifan Yang Qingqing Zhu Donald Wright Thomas Huang W. John Wilbur Zhe He Andrew Taylor Qingyu Chen et al. 2024. Agentmd: Empowering language agents for risk prediction with large-scale clinical tool learning. arXiv:2402.13225. Retrieved from https://arxiv.org/abs/2402.13225 · DOI
- Dongkyu Kim Byoungwook Kim Donggeon Han and Matouš Eibich. 2024. AutoRAG: Automated framework for optimization of retrieval augmented generation pipeline. arXiv:2410.20878. Retrieved from https://arxiv.org/abs/2410.20878 · arXiv
- Minsoo Kim, Victor Bursztyn, Eunyee Koh, Shunan Guo, and Seung-won Hwang. 2024. Rada: Retrieval-augmented web agent planning with llms. In Findings of the Association for Computational Linguistics ACL 2024. 13511–13525.
- Yubin Kim, Chanwoo Park, Hyewon Jeong, Yik Siu Chan, Xuhai Xu, Daniel McDuff, Hyeonhoon Lee, Marzyeh Ghassemi, Cynthia Breazeal, Hae Park, et al. 2025. Mdagents: An adaptive collaboration of llms for medical decision-making. Advances in Neural Information Processing Systems 37 (2025), 79410–79452.
- Jakub Lála Odhran O’Donoghue Aleksandar Shtedritski Sam Cox Samuel G. Rodriques and Andrew D. White. 2023. Paperqa: Retrieval-augmented generative agent for scientific research. arXiv:2312.07559. Retrieved from https://arxiv.org/abs/2312.07559 · arXiv
- Marc Lanctot Edward Lockhart Jean-Baptiste Lespiau Vinicius Zambaldi Satyaki Upadhyay Julien Pérolat Sriram Srinivasan Finbarr Timbers Karl Tuyls Shayegan Omidshafiei et al. 2019. OpenSpiel: A framework for reinforcement learning in games. arXiv:1908.09453. Retrieved from https://arxiv.org/abs/1908.09453 · arXiv
- Dong Won Lee, Hae Park, Yoon Kim, Cynthia Breazeal, and Louis-Philippe Morency. 2024. Global reward to local rewards: Multimodal-guided decomposition for improving dialogue agents. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 15737–15762.
- Binxu Li, Tiankai Yan, Yuanting Pan, Jie Luo, Ruiyang Ji, Jiayuan Ding, Zhe Xu, Shilong Liu, Haoyu Dong, Zihao Lin, et al. 2024. MMedAgent: Learning to use medical tools with multi-modal agent. In Findings of the Association for Computational Linguistics: EMNLP 2024. 8745–8760.
- Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, et al. 2025. From generation to judgment: Opportunities and challenges of llm-as-a-judge. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2757–2791.
- Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Ruiying Geng, Nan Huo, et al. 2023. Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls. Advances in Neural Information Processing Systems 36 (2023), 42330–42357.
- Ming Li, Yong Zhang, Zhitao Li, Jiuhai Chen, Lichang Chen, Ning Cheng, Jianzong Wang, Tianyi Zhou, and Jing Xiao. 2024. From quantity to quality: Boosting LLM performance with self-guided data selection for instruction tuning. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 7595–7628.
- Renhao Li, Minghuan Tan, Derek Wong, and Min Yang. 2024. CoEvol: Constructing better responses for instruction finetuning through multi-agent cooperation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 4703–4721.
- Xiaoxi Li Jiajie Jin Guanting Dong Hongjin Qian Yongkang Wu Ji-Rong Wen Yutao Zhu and Zhicheng Dou. 2025. Webthinker: Empowering large reasoning models with deep research capability. arXiv:2504.21776. Retrieved from https://arxiv.org/abs/2504.21776 · arXiv
- Zaijing Li, Yuquan Xie, Rui Shao, Gongwei Chen, Dongmei Jiang, and Liqiang Nie. 2024. Optimus-1: Hybrid multimodal memory empowered agents excel in long-horizon tasks. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 37. 49881–49913.
- Xuechen Liang Meiling Tao Yinghui Xia Tianyu Shi Jun Wang and JingSong Yang. 2024. Cmat: A multi-agent collaboration tuning framework for enhancing small language models. arXiv:2404.01663. Retrieved from https://arxiv.org/abs/2404.01663 · arXiv
- Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, Nouha Dziri, Melanie Sclar, Khyathi Chandu, Chandra Bhagavatula, and Yejin Choi. 2024. The unlocking spell on base LLMs: Rethinking alignment via in-context learning. In Proceedings of the 12th International Conference on Learning Representations.
- Evan Zheran Liu Kelvin Guu Panupong Pasupat Tianlin Shi and Percy Liang. 2018. Reinforcement learning on web interfaces using workflow-guided exploration. arXiv:1802.08802. Retrieved from https://arxiv.org/abs/1802.08802 · arXiv
- Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems 36 (2023), 34892–34916.
- Jie Liu, Pan Zhou, Yingjun Du, Ah-Hwee Tan, Cees G. M. Snoek, Jan-Jakob Sonke, and Efstratios Gavves. 2025. CaPo: Cooperative plan optimization for efficient embodied multi-agent cooperation. In Proceedings of the 13th International Conference on Learning Representations.
- Sizhe Liu Yizhou Lu Siyu Chen Xiyang Hu Jieyu Zhao Tianfan Fu and Yue Zhao. 2024. Drugagent: Automating ai-aided drug discovery programming through llm multi-agent collaboration. arXiv:2411.15692. Retrieved from https://arxiv.org/abs/2411.15692 · arXiv
- Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al. 2024. AgentBench: Evaluating LLMs as agents. In Proceedings of the 12th International Conference on Learning Representations.
- Yun-ting Liu, Jia-ming Yang, Liang Chen, Ting Guo, and Yu Jiang. 2020. Overview of reinforcement learning based on value and policy. In Proceedings of the 2020 Chinese Control And Decision Conference. IEEE, 598–603.
- Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, and Diyi Yang. 2024. A dynamic LLM-powered agent network for task-oriented agent collaboration. In Proceedings of the 1st Conference on Language Modeling.
- Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems 35 (2022), 2507–2521.
- Chang Ma, Junlei Zhang, Zhihao Zhu, Cheng Yang, Yujiu Yang, Yaohui Jin, Zhenzhong Lan, Lingpeng Kong, and Junxian He. 2024. AgentBoard: An analytical evaluation board of multi-turn LLM agents. In Proceedings of the 38th Conference on Neural Information Processing Systems Datasets and Benchmarks Track.
- Hao Ma Tianyi Hu Zhiqiang Pu Boyin Liu Xiaolin Ai Yanyan Liang and Min Chen. 2024. Coevolving with the other you: Fine-tuning LLM with sequential cooperative multi-agent reinforcement learning. arXiv:2410.06101. Retrieved from https://arxiv.org/abs/2410.06101 · arXiv
- 10.1109/ICRA57147.2024.10610855 · DOI · Paper page
- Karttikeya Mangalam, Raiymbek Akshulakov, and Jitendra Malik. 2023. Egoschema: A diagnostic benchmark for very long-form video language understanding. Advances in Neural Information Processing Systems 36 (2023), 46212–46244.
- Yuren Mao, Yuhang Ge, Yijiang Fan, Wenyi Xu, Yu Mi, Zhonghao Hu, and Yunjun Gao. 2025. A survey on lora of large language models. Frontiers of Computer Science 19, 7 (2025), 197605. · DOI
- Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2024. Gaia: A benchmark for general ai assistants. In Proceedings of the 12th International Conference on Learning Representations.
- Mahmoud Mohammadi, Yipeng Li, Jane Lo, and Wendy Yip. 2025. Evaluation and benchmarking of llm agents: A survey. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2. 6129–6139. · DOI · Paper page
- Ofir Nachum, Mohammad Norouzi, Kelvin Xu, and Dale Schuurmans. 2017. Bridging the gap between value and policy based reinforcement learning. Advances in Neural Information Processing Systems 30 (2017), 2772–2782.
- King Han Naman Jain Alex Gu Wen-Ding Li Fanjia Yan Tianjun Zhang Sida Wang Armando Solar-Lezama Koushik Sen and Ion Stoica. 2024. Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv:2403.07974. Retrieved from https://arxiv.org/abs/2403.07974 · arXiv
- OpenAI. 2024. GPT-4 Technical Report. arxiv:2303.08774. Retrieved from https://arxiv.org/abs/2303.08774 · arXiv
- Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730–27744.
- Jing-Cheng Pang, Si-Hang Yang, Kaiyuan Li, Jiaji Zhang, Xiong-Hui Chen, Nan Tang, and Yang Yu. 2024. KALM: Knowledgeable agents by offline reinforcement learning from large language model rollouts. In Proceedings of the Advances in Neural Information Processing Systems. 126620–126652.
- Jan Peters and Stefan Schaal. 2006. Policy gradient methods for robotics. In Proceedings of the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 2219–2225.
- Pranav Putta Edmund Mills Naman Garg Sumeet Motwani Chelsea Finn Divyansh Garg and Rafael Rafailov. 2024. Agent q: Advanced reasoning and learning for autonomous ai agents. arXiv:2408.07199. Retrieved from https://arxiv.org/abs/2408.07199 · arXiv
- Zehan Qi Xiao Liu Iat Long Iong Hanyu Lai Xueqiao Sun Wenyi Zhao Yu Yang Xinyue Yang Jiadai Sun Shuntian Yao et al. 2024. WebRL: Training LLM web agents via self-evolving online curriculum reinforcement learning. arXiv:2411.02337. Retrieved from https://arxiv.org/abs/2411.02337 · arXiv
- Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, YiFei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, and Maosong Sun. 2024. Experiential co-learning of software-developing agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 5628–5640. · DOI
- Chen Qian Zihao Xie Yifei Wang Wei Liu Yufan Dang Zhuoyun Du Weize Chen Cheng Yang Zhiyuan Liu and Maosong Sun. 2024. Scaling large-language-model-based multi-agent collaboration. arXiv:2406.07155. Retrieved from https://arxiv.org/abs/2406.07155 · arXiv
- Shuofei Qiao, Runnan Fang, Ningyu Zhang, Yuqi Zhu, Xiang Chen, Shumin Deng, Yong Jiang, Pengjun Xie, Fei Huang, and Huajun Chen. 2024. Agent planning with world knowledge model. Advances in Neural Information Processing Systems 37 (2024), 114843–114871.
- Shuofei Qiao, Ningyu Zhang, Runnan Fang, Yujie Luo, Wangchunshu Zhou, Yuchen Jiang, Chengfei Lv, and Huajun Chen. 2024. AutoAct: Automatic agent learning from scratch for QA via self-planning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 3003–3021. · DOI
- Yujia Qin Shihao Liang Yining Ye Kunlun Zhu Lan Yan Yaxi Lu Yankai Lin Xin Cong Xiangru Tang Bill Qian et al. 2023. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv:2307.16789. Retrieved from https://arxiv.org/abs/2307.16789 · arXiv
- Yuxiao Qu, Tianjun Zhang, Naman Garg, and Aviral Kumar. 2024. Recursive introspection: Teaching language model agents how to self-improve. Advances in Neural Information Processing Systems 37 (2024), 55249–55285.
- Yusuf Roohani Andrew Lee Qian Huang Jian Vora Zachary Steinhart Kexin Huang Alexander Marson Percy Liang and Jure Leskovec. 2024. Biodiscoveryagent: An ai agent for designing genetic perturbation experiments. arXiv:2405.17631. Retrieved from https://arxiv.org/abs/2405.17631 · arXiv
- 10.1007/978-3-031-20074-8_9 · DOI · Paper page
- Jinxin Shi Zongsheng Cao Runmin Ma Yusong Hu Jie Zhou Xin Li Lei Bai Liang He and Bo Zhang. 2025. DualResearch: Entropy-gated dual-graph retrieval for answer reconstruction. arXiv:2510.08959. Retrieved from https://arxiv.org/abs/2510.08959 · arXiv
- Wentao Shi Zichun Yu Fuli Feng Xiangnan He and Chenyan Xiong. 2025. Efficient multi-agent system training with data influence-oriented tree search. arXiv:2502.00955. Retrieved from https://arxiv.org/abs/2502.00955 · arXiv
- Wentao Shi, Mengqi Yuan, Junkang Wu, Qifan Wang, and Fuli Feng. 2024. Direct multi-turn preference optimization for language agents. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2312–2324.
- Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems 36 (2023), 8634–8652.
- Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk, Adam Trischler, and Matthew Hausknecht. 2021. ALFWorld: Aligning text and embodied environments for interactive learning. In Proceedings of the International Conference on Learning Representations.
- Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, and Sujian Li. 2024. AgentBank: Towards generalized LLM agents via fine-tuning on 50000+ interaction trajectories. In Findings of the Association for Computational Linguistics: EMNLP 2024. 2124–2141. · DOI
- Yifan Song, Da Yin, Xiang Yue, Jie Huang, Sujian Li, and Bill Yuchen Lin. 2024. Trial and error: Exploration-based trajectory optimization of LLM agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 7584–7600. · DOI
- Haoyang Su Renqi Chen Shixiang Tang Zhenfei Yin Xinzhe Zheng Jinzhe Li Biqing Qi Qi Wu Hui Li Wanli Ouyang Philip Torr Bowen Zhou and Nanqing Dong. 2024. Many heads are better than one: Improved scientific idea generation by a LLM-based multi-agent system. arXiv:2410.09403. Retrieved from https://arxiv.org/abs/2410.09403 · arXiv
- Vighnesh Subramaniam Yilun Du Joshua B. Tenenbaum Antonio Torralba Shuang Li and Igor Mordatch. 2025. Multiagent finetuning: Self improvement with diverse reasoning chains. arXiv:2501.05707. Retrieved from https://arxiv.org/abs/2501.05707 · arXiv
- Hao Sun, Jiayi Wu, Hengyi Cai, Xiaochi Wei, Yue Feng, Bo Wang, Shuaiqiang Wang, Yan Zhang, and Dawei Yin. 2024. AdaSwitch: Adaptive switching between small and large agents for effective cloud-local collaborative learning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 8052–8062. · DOI
- Richard S. Sutton, David McAllester, Satinder Singh, and Yishay Mansour. 1999. Policy gradient methods for reinforcement learning with function approximation. Advances in Neural Information Processing Systems 12 (1999), 1057–1063.
- Zhengwei Tao Ting-En Lin Xiancai Chen Hangyu Li Yuchuan Wu Yongbin Li Zhi Jin Fei Huang Dacheng Tao and Jingren Zhou. 2024. A survey on self-evolution of large language models. arXiv:2404.14387. Retrieved from https://arxiv.org/abs/2404.14387 · arXiv
- InternAgent Team, Bo Zhang, Shiyang Feng, Xiangchao Yan, Jiakang Yuan, Runmin Ma, Yusong Hu, Zhiyin Yu, Xiaohan He, Songtao Huang, et al. 2025. InternAgent: When agent becomes the scientist–building closed-loop system from hypothesis to verification. arXiv e-prints (2025), arXiv–2505.
- Dennis Ulmer Elman Mansimov Kaixiang Lin Justin Sun Xibin Gao and Yi Zhang. 2024. Bootstrapping llm-based task-oriented dialogue agents via self-talk. arXiv:2401.05033. Retrieved from https://arxiv.org/abs/2401.05033 · DOI
- Boshi Wang, Hao Fang, Jason Eisner, Benjamin Van Durme, and Yu Su. 2024. LLMs in the imaginarium: Tool learning through simulated trial and error. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 10583–10604. · DOI
- Guanzhi Wang Yuqi Xie Yunfan Jiang Ajay Mandlekar Chaowei Xiao Yuke Zhu Linxi Fan and Anima Anandkumar. 2023. Voyager: An open-ended embodied agent with large language models. arXiv:2305.16291. Retrieved from https://arxiv.org/abs/2305.16291 · arXiv
- Hanlin Wang, Chak Tou Leong, Jian Wang, and Wenjie Li. 2024. E2CL: Exploration-based error correction learning for embodied agents. In Findings of the Association for Computational Linguistics: EMNLP 2024. 7626–7639. · DOI
- Hanlin Wang Jian Wang Chak Tou Leong and Wenjie Li. 2025. Steca: Step-level trajectory calibration for llm agent learning. arXiv:2502.14276. Retrieved from https://arxiv.org/abs/2502.14276 · DOI
- Pei Wang Yanan Wu Zekun Wang Jiaheng Liu Xiaoshuai Song Zhongyuan Peng Ken Deng Chenchen Zhang Jiakai Wang Junran Peng et al. 2024. Mtu-bench: A multi-granularity tool-use benchmark for large language models. arXiv:2410.11710. Retrieved from https://arxiv.org/abs/2410.11710 · arXiv
- Renxi Wang Haonan Li Xudong Han Yixuan Zhang and Timothy Baldwin. 2024. Learning from failure: Integrating negative examples when fine-tuning large language models as agents. arXiv:2402.11651. Retrieved from https://arxiv.org/abs/2402.11651 · arXiv
- Xingyao Wang, Zihan Wang, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng, and Heng Ji. 2024. MINT: Evaluating LLMs in multi-turn interaction with tools and language feedback. In Proceedings of the 12th International Conference on Learning Representations. 1–35.
- Christopher J. C. H. Watkins and Peter Dayan. 1992. Q-learning. Machine Learning 8, 3–4 (1992), 279–292.
- Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V. Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824–24837.
- Muning Wen Ziyu Wan Weinan Zhang Jun Wang and Ying Wen. 2024. Reinforcing language agents via policy optimization with action decomposition. arXiv:2405.15821. Retrieved from https://arxiv.org/abs/2405.15821 · arXiv
- Cheng-Kuang Wu, Zhi Rui Tam, Chieh-Yen Lin, Yun-Nung Chen, and Hung-yi Lee. 2024. StreamBench: Towards benchmarking continuous improvement of language agents. In Proceedings of the 38th Conference on Neural Information Processing Systems Datasets and Benchmarks Track.
- Jialong Wu, Shaofeng Yin, Ningya Feng, Xu He, Dong Li, Jianye Hao, and Mingsheng Long. 2025. ivideogpt: Interactive videogpts are scalable world models. Advances in Neural Information Processing Systems 37 (2025), 68082–68119.
- Qingyun Wu Gagan Bansal Jieyu Zhang Yiran Wu Beibin Li Erkang Zhu Li Jiang Xiaoyun Zhang Shaokun Zhang Jiale Liu et al. 2023. Autogen: Enabling next-gen llm applications via multi-agent conversation. arXiv:2308.08155. Retrieved from https://arxiv.org/abs/2308.08155 · arXiv
- Shirley Wu, Shiyu Zhao, Qian Huang, Kexin Huang, Michihiro Yasunaga, Kaidi Cao, Vassilis Ioannidis, Karthik Subbian, Jure Leskovec, and James Y. Zou. 2025. AvaTaR: Optimizing LLM agents for tool usage via contrastive reasoning. Advances in Neural Information Processing Systems 37 (2025), 25981–26010.
- Zhiheng Xi Yiwen Ding Wenxiang Chen Boyang Hong Honglin Guo Junzhe Wang Dingwen Yang Chenyang Liao Xin Guo Wei He et al. 2024. AgentGym: Evolving large language model-based agents across diverse environments. arXiv:2406.04151. Retrieved from https://arxiv.org/abs/2406.04151 · arXiv
- Zhiheng Xi Jixuan Huang Chenyang Liao Baodai Huang Honglin Guo Jiaqi Liu Rui Zheng Junjie Ye Jiazheng Zhang Wenxiang Chen et al. 2025. Agentgym-rl: Training llm agents for long-horizon decision making through multi-turn reinforcement learning. arXiv:2509.08755. Retrieved from https://arxiv.org/abs/2509.08755 · arXiv
- Yufei Xiang, Yiqun Shen, Yeqin Zhang, and Nguyen Cam-Tu. 2024. Retrospex: Language agent meets offline reinforcement learning critic. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 4650–4666. · DOI
- 10.1109/CVPR46437.2021.00965 · DOI · Paper page
- Yihang Xiao Jinyi Liu Yan Zheng Xiaohan Xie Jianye Hao Mingzhi Li Ruitao Wang Fei Ni Yuxiao Li Jintian Luo et al. 2024. Cellagent: An llm-driven multi-agent framework for automated single-cell data analysis. arXiv:2407.09811. Retrieved from https://arxiv.org/abs/2407.09811 · DOI
- Yijia Xiao Edward Sun Di Luo and Wei Wang. 2024. TradingAgents: Multi-agents LLM financial trading framework. arXiv:2412.20138. Retrieved from https://arxiv.org/abs/2412.20138 · arXiv
- Ziyang Xiao, Dongxiang Zhang, Yangjun Wu, Lilin Xu, Yuan Jessica Wang, Xiongwei Han, Xiaojin Fu, Tao Zhong, Jia Zeng, Mingli Song, et al. 2023. Chain-of-experts: When llms meet complex operations research problems. In Proceedings of the 12th International Conference on Learning Representations.
- Weimin Xiong Yifan Song Qingxiu Dong Bingchan Zhao Feifan Song Xun Wang and Sujian Li. 2025. MPO: Boosting LLM agents with meta plan optimization. arXiv:2503.02682. Retrieved from https://arxiv.org/abs/2503.02682 · DOI
- Fangzhi Xu Qiushi Sun Kanzhi Cheng Jun Liu Yu Qiao and Zhiyong Wu. 2024. Interactive evolution: A neural-symbolic self-training framework for large language models. arXiv:2406.11736. Retrieved from https://arxiv.org/abs/2406.11736 · arXiv
- Renjun Xu and Jingwen Peng. 2025. A comprehensive survey of deep research: Systems methodologies and applications. arXiv:2506.12594. Retrieved from https://arxiv.org/abs/2506.12594 · arXiv
- Tianyang Xu, Shujin Wu, Shizhe Diao, Xiaoze Liu, Xingyao Wang, Yangyi Chen, and Jing Gao. 2024. SaySelf: Teaching LLMs to express confidence with self-reflective rationales. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 5985–5998.
- Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V. Le, Denny Zhou, and Xinyun Chen. 2024. Large language models as optimizers. In Proceedings of the 12th International Conference on Learning Representations, ICLR 2024.
- Hongyang Yang Boyu Zhang Neng Wang Cheng Guo Xiaoli Zhang Likun Lin Junlin Wang Tianyu Zhou Mao Guan Runjia Zhang et al. 2024. FinRobot: An open-source AI agent platform for financial applications using large language models. arXiv:2405.14767. Retrieved from https://arxiv.org/abs/2405.14767 · DOI
- John Yang, Carlos E. Jimenez, Alex L. Zhang, Kilian Lieret, Joyce Yang, Xindi Wu, Ori Press, Niklas Muennighoff, Gabriel Synnaeve, Karthik R. Narasimhan, et al. 2025. SWE-bench multimodal: Do AI systems generalize to visual software domains?. In Proceedings of the 13th International Conference on Learning Representations.
- John Yang, Akshara Prabhakar, Karthik Narasimhan, and Shunyu Yao. 2023. Intercode: Standardizing and benchmarking interactive coding with execution feedback. Advances in Neural Information Processing Systems 36 (2023), 23826–23854.
- 10.1109/CVPR52733.2024.02482 · DOI
- Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. 2022. Webshop: Towards scalable real-world web interaction with grounded language agents. Advances in Neural Information Processing Systems 35 (2022), 20744–20757.
- Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing reasoning and acting in language models. In Proceedings of the International Conference on Learning Representations.
- Weiran Yao Shelby Heinecke Juan Carlos Niebles Zhiwei Liu Yihao Feng Le Xue Rithesh Murthy Zeyuan Chen Jianguo Zhang Devansh Arpit et al. 2023. Retroformer: Retrospective large language agents with policy gradient optimization. arXiv:2308.02151. Retrieved from https://arxiv.org/abs/2308.02151 · arXiv
- 10.1093/bib/bbae693 · DOI
- Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, and Bill Yuchen Lin. 2024. Agent lumos: Unified and modular training for open-source language agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 12380–12403. · DOI · Paper page
- Yangyang Yu, Zhiyuan Yao, Haohang Li, Zhiyang Deng, Yuechen Jiang, Yupeng Cao, Zhi Chen, Jordan Suchow, Zhenyu Cui, Rong Liu, et al. 2025. Fincon: A synthesized llm multi-agent system with conceptual verbal reinforcement for enhanced financial decision making. Advances in Neural Information Processing Systems 37 (2025), 137010–137045.
- Ling Yue, Sixue Xing, Jintai Chen, and Tianfan Fu. 2024. Clinicalagent: Clinical trial multi-agent system with large language model-based reasoning. In Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. 1–10.
- Shengbin Yue Siyuan Wang Wei Chen Xuanjing Huang and Zhongyu Wei. 2024. Synergistic multi-agent framework with trajectory learning for knowledge-intensive tasks. arXiv:2407.09893. Retrieved from https://arxiv.org/abs/2407.09893 · arXiv
- Kamer Ali Yuksel and Hassan Sawaf. 2024. A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops. arXiv:2412.17149. Retrieved from https://arxiv.org/abs/2412.17149 · arXiv
- Aohan Zeng Mingdao Liu Rui Lu Bowen Wang Xiao Liu Yuxiao Dong and Jie Tang. 2023. Agenttuning: Enabling generalized agent abilities for llms. arXiv:2310.12823. Retrieved from https://arxiv.org/abs/2310.12823 · arXiv
- Daochen Zha Kwei-Herng Lai Yuanpu Cao Songyi Huang Ruzhe Wei Junyu Guo and Xia Hu. 2019. Rlcard: A toolkit for reinforcement learning in card games. arXiv:1910.04376. Retrieved from https://arxiv.org/abs/1910.04376 · arXiv
- Simon Zhai, Hao Bai, Zipeng Lin, Jiayi Pan, Peter Tong, Yifei Zhou, Alane Suhr, Saining Xie, Yann LeCun, Yi Ma, et al. 2024. Fine-tuning large vision-language models as decision-making agents via reinforcement learning. Advances in Neural Information Processing Systems 37 (2024), 110935–110971.
- Hongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua B. Tenenbaum, Tianmin Shu, and Chuang Gan. 2024. Building cooperative embodied agents modularly with large language models. In Proceedings of the International Conference on Learning Representations.
- Jianguo Zhang Tian Lan Rithesh Murthy Zhiwei Liu Weiran Yao Ming Zhu Juntao Tan Thai Hoang Zuxin Liu Liangwei Yang et al. 2024. Agentohana: Design unified data and training pipeline for effective agent learning. arXiv:2402.15506. Retrieved from https://arxiv.org/abs/2402.15506 · arXiv
- 10.1007/978-3-030-60990-0_12 · DOI · Paper page
- Qizheng Zhang Changran Hu Shubhangi Upasani Boyuan Ma Fenglu Hong Vamsidhar Kamanuru Jay Rainton Chen Wu Mengmeng Ji Hanchen Li et al. 2025. Agentic context engineering: Evolving contexts for self-improving language models. arXiv:2510.04618. Retrieved from https://arxiv.org/abs/2510.04618 · arXiv
- Shengyu Zhang Linfeng Dong Xiaoya Li Sen Zhang Xiaofei Sun Shuhe Wang Jiwei Li Runyi Hu Tianwei Zhang Fei Wu et al. 2023. Instruction tuning for large language models: A survey. arXiv:2308.10792. Retrieved from https://arxiv.org/abs/2308.10792 · arXiv
- Shaokun Zhang, Jieyu Zhang, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, and Qingyun Wu. 2024. Offline training of language model agents with functions as learnable weights. Proceedings of Machine Learning Research 235 (2024), 60315–60335.
- Wenqi Zhang, Ke Tang, Hai Wu, Mengna Wang, Yongliang Shen, Guiyang Hou, Zeqi Tan, Peng Li, Yueting Zhuang, and Weiming Lu. 2024. Agent-Pro: Learning to evolve via policy-level reflection and optimization. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 5348–5375. · DOI
- Wentao Zhang, Lingxuan Zhao, Haochong Xia, Shuo Sun, Jiaze Sun, Molei Qin, Xinyi Li, Yuqing Zhao, Yilei Zhao, Xinyu Cai, et al. 2024. A multimodal foundation agent for financial trading: Tool-augmented, diversified, and generalist. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 4314–4325. · DOI · Paper page
- Yiming Zhang Zheng Chang Wentao Cai MengXing Ren Kang Yuan Yining Sun and Zenghui Ding. 2025. IIMedGPT: Promoting large language model capabilities of medical tasks by efficient human preference alignment. arXiv:2501.02869. Retrieved from https://arxiv.org/abs/2501.02869 · arXiv
- Chuanyang Zheng, Haiming Wang, Enze Xie, Zhengying Liu, Jiankai Sun, Huajian Xin, Jianhao Shen, Zhenguo Li, and Yu Li. 2024. Lyra: Orchestrating dual correction in automated theorem proving. Transactions on Machine Learning Research (2024).
- Yuxiang Zheng Dayuan Fu Xiangkun Hu Xiaojie Cai Lyumanshan Ye Pengrui Lu and Pengfei Liu. 2025. Deepresearcher: Scaling deep research via reinforcement learning in real-world environments. arXiv:2504.03160. Retrieved from https://arxiv.org/abs/2504.03160 · DOI · Paper page
- Hang Zhou, Yehui Tang, Haochen Qin, Yujie Yang, Renren Jin, Deyi Xiong, Kai Han, and Yunhe Wang. 2024. Star-agents: Automatic data optimization with LLM agents for instruction tuning. Advances in Neural Information Processing Systems 37 (2024), 4575–4597.
- Han Zhou Xingchen Wan Ruoxi Sun Hamid Palangi Shariq Iqbal Ivan Vulić Anna Korhonen and Sercan Ö Arık. 2025. Multi-agent design: Optimizing agents with better prompts and topologies. arXiv:2502.02533. Retrieved from https://arxiv.org/abs/2502.02533 · arXiv
- Qinhao Zhou, Zihan Zhang, Xiang Xiang, Ke Wang, Yuchuan Wu, and Yongbin Li. 2024. Enhancing the general agent capabilities of low-paramter LLMs through tuning and multi-branch reasoning. In Findings of the Association for Computational Linguistics: NAACL 2024. 2922–2931. · DOI
- Wangchunshu Zhou Yixin Ou Shengwei Ding Long Li Jialong Wu Tiannan Wang Jiamin Chen Shuai Wang Xiaohua Xu Ningyu Zhang et al. 2024. Symbolic learning enables self-evolving agents. arXiv:2406.18532. Retrieved from https://arxiv.org/abs/2406.18532 · arXiv
- Junda Zhu, Lingyong Yan, Haibo Shi, Dawei Yin, and Lei Sha. 2024. ATM: Adversarial tuning multi-agent system makes a robust retrieval-augmented generator. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 10902–10919.
- Kaiwen Zuo Yirui Jiang Fan Mo and Pietro Lio. 2024. KG4Diagnosis: A hierarchical multi-agent LLM framework with knowledge graph enhancement for medical diagnosis. arXiv:2412.16833. Retrieved from https://arxiv.org/abs/2412.16833 · arXiv
Cited by
A Survey of Context Engineering for Large Language Models
Mei, L., Yao, J., Ge, Y., Wang, Y., Bi, B., Cai, Y., Liu, J., Li, M., Li, Z.-Z., Zhang, D., et al. (2025) · arXiv · doi:10.48550/arxiv.2507.13334 · Cited by 281
Li, Z., Li, Z., Shi, Y., Wang, R., Yang, J., Liu, Z., Wu, X., Li, A., Huang, C., Shang, E., et al. (2026) · arXiv · doi:10.48550/arxiv.2607.08964 · Cited by 46
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
Yue, L., Bhandari, K. R., Ko, C.-Y., Patel, D., Lin, S., Zhou, N., Gao, J., Chen, P.-Y., & Pan, S. (2026) · arXiv · doi:10.48550/arxiv.2603.22386 · Cited by 1
“Broader optimization surveys cover many ways to improve LLM agents, often through the lens of parameter-driven versus parameter-free methods (Du et al., 2026; Yue et al., 2026).”
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
Du, S., Yan, X., Shi, J., Cao, Z., Feng, S., Liang, Z., Sun, B., Guo, X., Peng, T., Zhou, Y., et al. (2026) · arXiv · doi:10.48550/arxiv.2606.06473 · Cited by 31
Self-citationWolff, B., & Bennati, J. (2026) · arXiv · doi:10.48550/arxiv.2601.07978
“Mem0 extracts salient facts via LLM calls against a rolling conversation summary, then reconciles them with semantically similar entries in a vector store through tool-call operations that add, update, delete, or skip memories [13].”
Metadata
- Authors
- Du, S., Zhao, J., Shi, J., Xie, Z., Jiang, X., Bai, Y., & He, L.
- Venue
- ACM Computing Surveys
- Published
- 2026-02-11
- Volume
- 58
- Issue
- 9
- Pages
- 1-37
- ISSN
- 0360-0300
- 1557-7341
- Cited by
- 26
- References
- 58
- Language
- en
- Funders
- National Natural Science Foundation of China (62477011, 62207013)
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A Survey on the Optimization of Large Language Model-based Agents. https://app.cochat.ai/papers/10.1145/3789261
- The paper
- Du, S., Zhao, J., Shi, J., Xie, Z., Jiang, X., Bai, Y., & He, L. (2026). A Survey on the Optimization of Large Language Model-based Agents. ACM Computing Surveys. https://doi.org/10.1145/3789261
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.