導(dǎo)語

當(dāng)前人工智能領(lǐng)域正在經(jīng)歷一場從“機械執(zhí)行”到“自主認(rèn)知”的深刻范式變革，這場變革正在從根本上重塑我們對智能系統(tǒng)的理解、設(shè)計和應(yīng)用方式。隨著大模型技術(shù)的突破性發(fā)展及其在復(fù)雜系統(tǒng)建模中的廣泛應(yīng)用，多智能體系統(tǒng)（Multi-Agent Systems, MAS）的研究正經(jīng)歷著前所未有的轉(zhuǎn)型——從傳統(tǒng)的基于固定規(guī)則的建模（Agent-Based Modeling, ABM）向由LLM驅(qū)動的、具備自主認(rèn)知能力的智能體范式演進。這一轉(zhuǎn)變不僅帶來了技術(shù)架構(gòu)的根本性革命，使智能體具備了類人的推理能力、動態(tài)適應(yīng)能力和復(fù)雜社交能力，更開創(chuàng)了復(fù)雜系統(tǒng)研究的新紀(jì)元。

大模型賦能的智能體展現(xiàn)出三大革命性特征：認(rèn)知深度（能夠進行類人的推理和決策，甚至展現(xiàn)出記憶、學(xué)習(xí)和個性特征）、動態(tài)交互（基于自然語言的自主協(xié)商和社交行為）以及涌現(xiàn)行為（微觀交互產(chǎn)生更復(fù)雜的宏觀社會現(xiàn)象）。這些特性使得我們可以構(gòu)建前所未有的"高保真社會模擬器"，為理解經(jīng)濟、社會、管理、軍事等復(fù)雜系統(tǒng)提供了全新視角。

因此，集智俱樂部聯(lián)合山東工商學(xué)院副教授高德華、天津大學(xué)教授薛霄、北京師范大學(xué)張江、國防科技大學(xué)博士研究生曾利共同發(fā)起「大模型時代下的Agent建模與仿真」讀書會。讀書會自2025年7月8日開始，每周二晚上7:30-9:30進行，預(yù)計持續(xù)分享8周左右。掃碼加入Agent建模與仿真的前沿探索之旅，一起共學(xué)、共創(chuàng)、共建、共享「大模型時代下的Agent建模與仿真」社區(qū)，共同暢想大模型時代人工社會的未來圖景！

讀書會背景

過去幾十年里，社會科學(xué)家和相關(guān)領(lǐng)域的研究者，一直致力于通過實證數(shù)據(jù)與模型揭示人類行為和智能社會運行的基本規(guī)律，試圖找出隱藏在各種社會現(xiàn)象和治理痛點背后的因果機制，從而回答“是什么”、“為什么”、“如何治”等一系列問題。Agent建模與仿真作為一種科學(xué)方法論在上世紀(jì)八九十年代被提出。其核心思想是借助于計算機平臺，在一個人工搭建的虛擬環(huán)境中創(chuàng)建若干彼此之間以及與環(huán)境之間能夠交互的Agent，對現(xiàn)實個體行為與環(huán)境進行精細(xì)刻畫，進而輔助研究者的直覺推理。

科學(xué)家們圍繞經(jīng)濟學(xué)等社會科學(xué)及工程領(lǐng)域廣泛存在的復(fù)雜系統(tǒng)和復(fù)雜現(xiàn)象所開展的探索工作，如Joshua Epstein 等開發(fā)的糖域模型、Brain Arthur 領(lǐng)導(dǎo)開發(fā)的人工股票市場模型、Thomas Schelling 的居住隔離模型、Christopher Langton 的人工生命模型都是在這一時期提出和發(fā)展起來的。

讀書會介紹

伴隨著ChatGPT、DeepSeek這樣的大語言模型的興起，Agent建模與仿真的能力迎來重大躍升。我們不僅可以實現(xiàn)從微觀個體行動到宏觀群體行為與決策效應(yīng)/模式的低成本、高可控的探索性模擬研究，揭示復(fù)雜系統(tǒng)的非線性、動態(tài)性和不確定性等重要特征。還可以通過觀察它們合作、競爭、學(xué)習(xí)、自我修正的行為，加深對大模型的理解，為其策略和動機建立可解釋機制，抵御可能的安全、倫理等不可逆風(fēng)險。

在這八周左右的時間里，山東工商學(xué)院副教授高德華、天津大學(xué)教授薛霄、北京師范大學(xué)張江、國防科技大學(xué)博士研究生曾利帶領(lǐng)大家通過經(jīng)典、前沿文獻領(lǐng)讀，帶你一起學(xué)習(xí)與追問。

核心問題

1. Agent建模與仿真是什么，核心技術(shù)發(fā)生了怎樣的演變？

2. 大模型時代，Agent建模與仿真會給復(fù)雜系統(tǒng)理論帶來哪些突破？

3. 大模型如何賦能Agent實現(xiàn)自主思考與動態(tài)適應(yīng)？

4. 大模型驅(qū)動的Agent交互會涌現(xiàn)出什么新型的社會現(xiàn)象？

5. Agent建模與仿真如何改變金融、心理、管理、軍事等領(lǐng)域的研究范式？

你將收獲

1. 梳理Agent建模與仿真的歷史發(fā)展脈絡(luò)與方法論；

2. 掌握一套理解、分析、控制、預(yù)測復(fù)雜系統(tǒng)的計算實驗框架；

3. 掌握基于多主體強化學(xué)習(xí)的復(fù)雜系統(tǒng)優(yōu)化方法；

4. 領(lǐng)略領(lǐng)域前沿學(xué)者的研究體系與科研路徑。

讀書會框架

發(fā)起人團隊

高德華，山東工商學(xué)院管理科學(xué)與工程學(xué)院副教授，管理學(xué)博士，碩士生導(dǎo)師。中國仿真學(xué)會離散系統(tǒng)仿真專業(yè)委員會會員、歐洲組織研究學(xué)會（EGOS）會員、亞洲社會仿真學(xué)會（ASSA）創(chuàng)始會員兼副秘書長。以第一/通訊作者先后在《公共管理學(xué)報》、《系統(tǒng)科學(xué)學(xué)報》、《Computational and Mathematical Organization Theory》、《Journal of Artificial Societies and Social Simulation》等國內(nèi)外學(xué)術(shù)期刊和學(xué)術(shù)會議上公開發(fā)表論文30多篇，參與編撰《Oxford Handbook of Agent-based Computational Management Science》（2024）和《Cambridge Handbook of Routine Dynamics》（2021）兩部Handbook，主持完成山東省自然科學(xué)基金項目2項，參與國家自然科學(xué)基金和國家社會科學(xué)基金等多項科研課題。

研究方向：計算組織科學(xué)、復(fù)雜組織決策與智能管理、工業(yè)系統(tǒng)工程。

薛霄，天津大學(xué)智能與計算學(xué)部，教授、博導(dǎo)。先后獲得第八屆楊嘉墀科技獎，2023年度IFAC 社會計算杰出成就獎，2023年 CCF服務(wù)計算杰出成就獎，省科技創(chuàng)新杰出青年(省杰青), 省高校科技創(chuàng)新人才，省高校青年骨干教師，省學(xué)術(shù)帶頭人等榮譽稱號。目前兼任：天津市健康人居環(huán)境與智慧技術(shù)重點實驗室副主任；中國自動化學(xué)會計算社會與社會智能專委會副主任；IEEE Transactions on Intelligent Vehicles 編委；International Journal of Crowd Science 編委；Complex System Modeling and Simulation青年編委。 近年來，主持與參與科研項目包括國家重點研發(fā)、國防特區(qū)創(chuàng)新、國家自然基金重點、國家自然基金面上、省級重大課題30多項；以第一作者或通信作者在IEEE Trans等頂級期刊與會議上發(fā)表論文60多篇，并獲得ICWS 2020最佳論文獎（服務(wù)計算Top 1會議）；2021年計算機研究與發(fā)展 Top10 高被引論文；出版著作《復(fù)雜系統(tǒng)的計算實驗方法》，是國內(nèi)第一本對計算實驗方法進行系統(tǒng)化梳理的專著；獲2023年度IFAC TC Award for Outstanding Achievement in Social Computing and CPSS。獲省自然科學(xué)二等獎2項（均排名第一）、省決策成果二等獎1項（排名第一）、省優(yōu)秀學(xué)術(shù)著作一等獎1項（獨著）。

研究方向：主要研究方向為服務(wù)計算、計算實驗、AI Agent、群體智能。

張江，北京師范大學(xué)系統(tǒng)科學(xué)學(xué)院教授，集智俱樂部、集智學(xué)園創(chuàng)始人，集智科學(xué)研究中心理事長，曾任騰訊研究院、華為戰(zhàn)略研究院等特聘顧問。

研究方向：因果涌現(xiàn)、復(fù)雜系統(tǒng)分析與建模、規(guī)模理論等。

曾利，國防科技大學(xué)系統(tǒng)工程在讀博士生。

研究方向：研究方向為強化學(xué)習(xí)、組合優(yōu)化、復(fù)雜網(wǎng)絡(luò)。

報名參與讀書會

運行模式

從2025年7月8日開始，每周二晚 19:30-21:30，持續(xù)時間預(yù)計8周左右，按讀書會框架設(shè)計，每周進行線上會議，與主講人等社區(qū)成員當(dāng)面交流，會后可以獲得視頻回放持續(xù)學(xué)習(xí)。

報名方式

第一步：微信掃碼填寫報名信息。

掃碼報名（可開發(fā)票）

第二步：填寫信息后，付費報名。如需用支付寶支付，請在PC端進入讀書會頁面報名支付：https://pattern.swarma.org/study_group/64

第三步：添加運營負(fù)責(zé)人微信，拉入對應(yīng)主題的讀書會社區(qū)（微信群）。

PS：為確保專業(yè)性和討論的聚焦，本讀書會謝絕脫離讀書會主題和復(fù)雜科學(xué)問題本身的空泛的哲學(xué)和思辨式討論；如果出現(xiàn)討論內(nèi)容不符合要求、經(jīng)提醒無效者，會被移除群聊并對未參與部分退費。

加入社區(qū)后可以獲得的資源：

完整權(quán)限，包括線上問答、錄播回看、資料共享、社群交流、信息同步、共創(chuàng)任務(wù)獲取積分等。

參與共創(chuàng)任務(wù)獲取積分，共建學(xué)術(shù)社區(qū)：

讀書會采用共學(xué)共研機制，成員通過內(nèi)容共創(chuàng)獲積分（字幕修改、讀書會筆記、論文速遞、公眾號文章、集智百科、論文解讀等共創(chuàng)任務(wù)），積分符合條件即可退費。發(fā)起人和主講人同樣遵循此機制，無額外金錢激勵。

PS：具體參與方式可以加入讀書會后查看對應(yīng)的共創(chuàng)任務(wù)列表，領(lǐng)取任務(wù)，與運營負(fù)責(zé)人溝通詳情，上述規(guī)則的最終解釋權(quán)歸集智俱樂部所有。

讀書會閱讀材料

閱讀材料較長，為了更好的閱讀體驗，建議您前往集智斑圖沉浸式閱讀，并可收藏感興趣的論文。

https://pattern.swarma.org/article/352?from=wechat

讀書會閱讀清單

Ageng建模與仿真概述

Elsenbroich, C., & Polhill, J. G. (2023). Agent-based modelling as a method for prediction in complex social systems. International Journal of Social Research Methodology, 26(2), 133–142.

An, L., Grimm, V., Sullivan, A., Turner?II, B. L., Malleson, N., et al. (2021). Challenges, tasks, and opportunities in modeling agent-based complex systems. Ecological Modelling, 457, 109685.

Stefan Thurner, Rudolf Hanel, and Peter Klimek. Introduction to the Theory of Complex Systems. Oxford University Press, 2018

Gagliolo, M. (2017). Simulate this! An Introduction to agent-based models and their power to iImprove your research practice. International Review of Social Psychology, 30(1)

Macal, C. M. (2016). Everything you need to know about agent-based modelling and simulation. Journal of Simulation, 10(2), 144–156.

Smaldino, P. E., Calanchini, J., & Pickett, C. L. (2015). Theory development with agent-based models. Organizational Psychology Review, 5(4), 300–317.

John H. Miller. Complex Adaptive Systems : An Introduction to Computational Models of Social Life. Princeton University Press, 2011

Bonabeau, E. (2002). Agent-based modeling: Methods and techniques for simulating human systems. Proceedings of the National Academy of Sciences, 99(suppl 3), 7280–7287.

計算實驗方法框架

薛霄, 于湘凝, 周德雨, 彭超, 王曉, 周長兵, 王飛躍. 計算實驗方法的溯源、現(xiàn)狀與展望, 自動化學(xué)報, 2023, 49(2): 246-271.

Xiao Xue, Deyu Zhou, Xiangning Yu, Gang Wang, Juanjuan Li, Xia Xie, Lizhen Cui, Fei-Yue Wang. Computational Experiments for Complex Social Systems: Experiment Design and Generative Explanation, IEEE/CAA Journal of Automatica Sinica, 2024, 11(4):1022-1038.

盛昭瀚, 張維. 管理科學(xué)研究中的計算實驗方法[J]. 管理科學(xué)學(xué)報, 2011,14(05):1-10

模型的校驗與驗證

Berger, U., Bell, A., Barton, C. M., Chappin, E., Dre?ler, G., et al. (2024). Towards reusable building blocks for agent-based modelling and theory development. Environmental Modelling & Software, 175, 106003.

Min Lu, Shizhan Chen, Xiao Xue, Xiao Wang, Yufang Zhang, Feiyue Wang. Computational Experiments for Complex Social System Part II: the Evaluation of Computational Model, IEEE Transactions on Computational Social Systems, 2022, 9(4): 1224-1236.

Istrate, G. (2021). Models We Can Trust: Toward a Systematic Discipline of (Agent-Based) Model Interpretation and Validation. Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems.

Sargent, R. G. (2020). Verification And Validation Of Simulation Models: An Advanced Tutorial. 2020 Winter Simulation Conference (WSC), 16–29.

Lux, T., & Zwinkels, R. C. J. (2018). Empirical Validation of Agent-Based Models. In C. Hommes & B. LeBaron (Eds.), Handbook of Computational Economics (Vol. 4, pp. 437–488). Elsevier.

Donkin, E., Dennis, P., Ustalakov, A., Warren, J., & Clare, A. (2017). Replicating complex agent based models, a formidable task. Environmental Modelling & Software, 92, 142–151.

Galán, J. M., Izquierdo, L. R., Izquierdo, S. S., Santos, J. I., del Olmo, R., et al. (2013). Checking Simulations: Detecting and Avoiding Errors and Artefacts. In B. Edmonds & R. Meyer (Eds.), Simulating Social Complexity: A Handbook (pp. 95–116). Springer.

Sargent, R. G. (2013). Verification and validation of simulation models. Journal of Simulation, 7(1), 12–24.

Midgley, D., Marks, R., & Kunchamwar, D. (2007). Building and assurance of agent-based models: An example and challenge to the field. Journal of Business Research, 60(8), 884–893.

Bianchi, C., Cirillo, P., Gallegati, M., & Vagliasindi, P. A. (2007). Validating and Calibrating Agent-Based Models: A Case Study. Computational Economics, 30(3), 245–264.

Wilensky, U., & Rand, W. (2007). Making Models Match: Replicating an Agent-Based Model. Journal of Artificial Societies and Social Simulation, 10(4):2. https://www.jasss.org/10/4/2.html

模型的可重復(fù)性

Berger, U., Bell, A., Barton, C. M., Chappin, E., Dre?ler, G., et al. (2024). Towards reusable building blocks for agent-based modelling and theory development. Environmental Modelling & Software, 175, 106003.

Donkin, E., Dennis, P., Ustalakov, A., Warren, J., & Clare, A. (2017). Replicating complex agent based models, a formidable task. Environmental Modelling & Software, 92, 142–151.

Wilensky, U., & Rand, W. (2007). Making Models Match: Replicating an Agent-Based Model. Journal of Artificial Societies and Social Simulation, 10(4):2. https://www.jasss.org/10/4/2.html

Agent建模與仿真+復(fù)雜網(wǎng)絡(luò)

吳江，社會網(wǎng)絡(luò)計算，2023，電子工業(yè)出版社.

Xiao Xue, Xiangning Yu, Deyu Zhou, Xiao Wang, Chongke Bi, Shufang Wang, Fei-Yue Wang. Computational Experiments for Complex Social Systems: Integrated Design of Experiment System, IEEE/CAA Journal of Automatica Sinica, 2024, 11(5):1175-1189.

吳江，社會網(wǎng)絡(luò)的動態(tài)分析與仿真實驗：理論與應(yīng)用，2012，武漢大學(xué)出版社.

Agent建模與仿真+強化學(xué)習(xí)

強化學(xué)習(xí)部分文獻

Mazyavkina, Nina, et al. "Reinforcement learning for combinatorial optimization: A survey." Computers & Operations Research 134 (2021): 105400.

Mnih, V., Kavukcuoglu, K., Silver, D. et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015). https://doi.org/10.1038/nature14236

Khalil, E.B., Dai, H., Zhang, Y., Dilkina, B.N., & Song, L. (2017). Learning Combinatorial Optimization Algorithms over Graphs. ArXiv, abs/1704.01665.

Fan, C., Zeng, L., Sun, Y. et al. Finding key players in complex networks through deep reinforcement learning. Nat Mach Intell 2, 317–324 (2020). https://doi.org/10.1038/s42256-020-0177-2

Fan, C., Shen, M., Nussinov, Z. et al. Searching for spin glass ground states through deep reinforcement learning. Nat Commun 14, 725 (2023). https://doi.org/10.1038/s41467-023-36363-w

多主體強化學(xué)習(xí)文獻推薦

Gronauer, Sven, and Klaus Diepold. "Multi-agent deep reinforcement learning: a survey." Artificial Intelligence Review 55.2 (2022): 895-943.（文獻綜述）

Perolat, Julien, et al. "Mastering the game of Stratego with model-free multiagent reinforcement learning." Science 378.6623 (2022): 990-996.（經(jīng)典論文）

The AI Economist: Taxation policy design via two-level deep multiagent reinforcement learning (集智上之前有介紹過這篇文獻)

Yang, Yaodong, et al. "Mean field multi-agent reinforcement learning." International conference on machine learning. PMLR, 2018. （經(jīng)典MARL算法）

Wen, Muning, et al. "Multi-agent reinforcement learning is a sequence modeling problem." Advances in Neural Information Processing Systems 35 (2022): 16509-16521. （頂會論文）

Hu, Shengchao, et al. "Learning multi-agent communication from graph modeling perspective." arXiv preprint arXiv:2405.08550 (2024). （頂會論文）

多主體建模+強化學(xué)習(xí)相結(jié)合的文獻

Brusatin, Simone, et al. "Simulating the economic impact of rationality through reinforcement learning and agent-based modelling." Proceedings of the 5th ACM International Conference on AI in Finance. 2024.

Li, Feixue, et al. "An agent-based learning-embedded model (ABM-learning) for urban land use planning: A case study of residential land growth simulation in Shenzhen, China." Land Use Policy 95 (2020): 104620.

Sert, Egemen, Yaneer Bar-Yam, and Alfredo J. Morales. "Segregation dynamics with reinforcement learning and agent based modeling." Scientific reports 10.1 (2020): 11771.

Zhang, Wei, Andrea Valencia, and Ni-Bin Chang. "Synergistic integration between machine learning and agent-based modeling: A multidisciplinary review." IEEE Transactions on Neural Networks and Learning Systems 34.5 (2021): 2170-2190. （ML+ABM綜述文章）

大模型與多智能體強化（或思想）學(xué)習(xí)結(jié)合的文獻

Bilal, Ahsan, et al. "Meta-thinking in llms via multi-agent reinforcement learning: A survey." arXiv preprint arXiv:2504.14520 (2025). （LLM+MARL）

Surina, Anja, et al. "Algorithm discovery with llms: Evolutionary search meets reinforcement learning." arXiv preprint arXiv:2504.05108 (2025). （LLM+RL 用于算法自動發(fā)現(xiàn) 被AlphaEvolve引用的文獻）

Zhang, Jiayi, et al. "Aflow: Automating agentic workflow generation." arXiv preprint arXiv:2410.10762 (2024). （頂會文章ICLR2025 RL For LLM Agent 蒙特卡洛數(shù)搜索用于智能體工作流優(yōu)化）

Yamada, Yutaro, et al. "The ai scientist-v2: Workshop-level automated scientific discovery via agentic tree search." arXiv preprint arXiv:2504.08066 (2025).（LLM Agent for Science）

多智能體大模型用于科學(xué)研究文獻推薦

Yu, Haofei, et al. "ResearchTown: Simulator of Human Research Community." arXiv preprint arXiv:2412.17767 (2024).

Schmidgall, Samuel, et al. "Agent laboratory: Using llm agents as research assistants." arXiv preprint arXiv:2501.04227 (2025).

Zhou, Zekun, et al. "From hypothesis to publication: A comprehensive survey of ai-driven research support systems." arXiv preprint arXiv:2503.01424 (2025).（綜述文獻 LLM Agent 用于自動研究 )

Amine Ferrag, Mohamed, Norbert Tihanyi, and Merouane Debbah. "From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review." arXiv e-prints (2025): arXiv-2504. （Autonomous AI Agents文獻綜述）

Agent建模與仿真+因果推斷

Manzo, G. (2022). Agent-based models and causal inference. John Wiley & Sons, Inc.

提出因果ABM（Causal Agent-Based Models）來推導(dǎo)描述復(fù)雜潛在行為現(xiàn)象的因果結(jié)構(gòu)。

Valogianni, Konstantina, and Balaji Padmanabhan. "Causal abms: Learning plausible causal models using agent-based modeling." The KDD'22 Workshop on Causal Discovery. PMLR, 2022.

Agent建模與仿真+大模型

Tsvetkova M, Yasseri T, Pescetelli N, et al. A new sociology of humans and machines[J]. Nature Human Behaviour, 2024, 8(10): 1864-1876.

Gao, C., Lan, X., Li, N., Yuan, Y., Ding, J., et al. (2024). Large language models empowered agent-based modeling and simulation: A survey and perspectives. Humanities and Social Sciences Communications, 11(1), 1–24.

Li, N., Gao, C., Li, M., Li, Y., & Liao, Q. (2023, October 16). EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities.

Lu, Y., Aleta, A., Du, C., Shi, L., & Moreno, Y. (2024). LLMs and generative agent-based models for complex systems research. Physics of Life Reviews, 51, 283–293.

Mou, X., Ding, X., He, Q., Wang, L., Liang, J., et al. (2024, December 4). From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents. https://doi.org/10.48550/arXiv.2412.03563

Zheng, W., & Tang, X. (2025). Simulating Social Network with LLM Agents: An Analysis of Information Propagation and Echo Chambers. In X. Tang, V. N. Huynh, H. Xia, & Q. Bai (Eds.), Knowledge and Systems Sciences (pp. 63–77). Springer Nature.

Xiao Xue, Shufang Wang, Lejun Zhang, Zhiyong Feng, Yaodan Guo. Social Learning Evolution (SLE): Computational Experiment-based Modeling Framework of Social Manufacturing. IEEE Transactions on Industrial Informatics, 2019, 15(6): 3343-3355.

Deyu Zhou, Xiao Xue, Zhangbin Zhou. SLE2: The improved Social Learning Evolution Model of Cloud Manufacturing Service Ecosystem, DOI=10.1109/TII.2022.3173053, IEEE Transactions on Industrial Informatics, 2022, 18(12): 9017-9026.

Deyu Zhou, Xiao Xue, Xudong Lu, Yuwei Guo, Peilin Ji, Hongtao Lv, Wei He, Yonghui Xu, Qingzhong Li, Lizhen Cui. A Hierarchical Model for Complex Adaptive System: From Generative Agent to AI Society, ACM Transactions on Autonomous and Adaptive Systems, https://doi.org/10.1145/3686802, 2024.

Xiao Xue, Fang-Yi Chen, De-Yu Zhou, Xiao Wang, Min Lu, Fei-Yue Wang. Computational Experiments for Complex Social Systems Part I: The Customization of Computational Model, IEEE Transactions on Computational Social Systems, 2022, 9(5): 1330-1344.

Ale Ebrahim Dehkordi, M., Lechner, J., Ghorbani, A., Nikolic, I., Chappin, é., et al. (2023). Using Machine Learning for Agent Specifications in ABM: A Critical Review and Guidelines. Journal of Artificial Societies and Social Simulation, 26(1), 9.

An, L., Grimm, V., Bai, Y., Sullivan, A., Turner, B. L., et al. (2023). Modeling agent decision and behavior in the light of data science and artificial intelligence. Environmental Modelling & Software, 105713.

Lamperti, F., Roventini, A., & Sani, A. (2018). Agent-based model calibration using machine learning surrogates. Journal of Economic Dynamics and Control, 90, 366–389.

Monti, C., Pangallo, M., De Francisci Morales, G., & Bonchi, F. (2023). On learning agent-based models from data. Scientific Reports, 13(1)

Zhang, W., Valencia, A., & Chang, N.-B. (2023). Synergistic Integration Between Machine Learning and Agent-Based Modeling: A Multidisciplinary Review. IEEE Transactions on Neural Networks and Learning Systems, 34(5), 2170–2190.

領(lǐng)域?qū)嵺`金融學(xué)

Axtell, R. L., & Farmer, J. D. (2023). Agent-Based Modeling in Economics and Finance: Past, Present, and Future. Journal of Economic Literature. https://doi.org/10.1257/jel.20221319

Bertani, F., Ponta, L., Raberto, M., Teglio, A., & Cincotti, S. (2021). The complexity of the intangible digital economy: An agent-based model. Journal of Business Research, 129, 527–540.

Farmer, J. D., & Foley, D. (2009). The economy needs agent-based modelling. Nature, 460(7256), 685–686.

Tesfatsion, L. (2023). Agent-Based Computational Economics: Overview and Brief History. In R. Venkatachalam (Ed.), Artificial Intelligence, Learning and Computation in Economics and Finance (pp. 41–58). Springer International Publishing.

組織與管理科學(xué)

Blanco-Fernández, D., Leitner, S., & Rausch, A. (2025). Interactions between dynamic team composition and coordination: An agent-based modeling approach. Review of Managerial Science, 19, 1–37.

Wu, J., Ohya, T., & Sekiguchi, T. (2024). Applications of agent-based modeling and simulation in organization management: A quarter-century review through bibliometric mapping (1998–2022). Computational and Mathematical Organization Theory, 30, 1–31.

Onggo, B. S., & Foramitti, J. (2021). Agent-Based Modeling and Simulation For Business and Management: A Review and Tutorial. 2021 Winter Simulation Conference (WSC), 1–15. 2021 Winter Simulation Conference (WSC).

Choi, T., & Park, S. (2021). Theory building via agent-based modeling in public administration research: Vindications and limitations. International Journal of Public Sector Management, 34(6), 614–629.

Gómez-Cruz, N. A., Loaiza Saa, I., & Ortega Hurtado, F. F. (2017). Agent-based simulation in management and organizational studies: A survey. European Journal of Management and Business Economics, 26(3), 313–328.

Wall, F. (2016). Agent-based modeling in managerial science: An illustrative survey and study. Review of Managerial Science, 10(1), 135–193.

Secchi D, Neumann M. (2016). Agent-Based Simulation of Organizational Behavior: New Frontiers of Social Science Research. Springer.

Fioretti, G. (2013). Agent-Based Simulation Models in Organization Science. Organizational Research Methods, 16(2), 227–242.

Gao, D. (2024). Using agent-based modeling for theory building in organizational routines. In: Chen, S., Wall, F. & Leitner, S. (eds.), The Oxford Handbook of Agent-based Computational Management Science, Oxford, UK: Oxford University Press

軍事學(xué)

在多智能體游戲環(huán)境中評估大語言模型的決策能力至關(guān)重要。本文提出的 GAMA (γ)-Bench 框架，通過八大經(jīng)典博弈場景動態(tài)評估 LLM，揭示模型在策略推理與泛化能力上的差異，為理解 LLM 決策智能提供了全新視角。

Huang, Jen-tse, et al. "Competing large language models in multi-agent gaming environments." The Thirteenth International Conference on Learning Representations. 2025.

張洪廣, et al."大模型驅(qū)動的智能輔助決策原理與典型應(yīng)用."指揮與控制學(xué)報 10.06(2024):661-668.

Wenyue Hua, Lizhou Fan, Lingyao Li, et al.War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars. arXiv:2311.17227, 2024

羅俊仁, et al."智能推演綜述：博弈論視角下的戰(zhàn)術(shù)戰(zhàn)役兵棋與戰(zhàn)略博弈."系統(tǒng)仿真學(xué)報 35.09(2023):1871-1894.doi:10.16182/j.issn1004731x.joss.23-0300.

夏立平."雙層博弈理論視閾下特朗普政府的朝核政策."美國研究 31.06(2017):123-140+8.

心理學(xué)

伍海燕, et al. "大語言模型的情感智能及其心理學(xué)應(yīng)用." 科技導(dǎo)報 43.3 (2025): 47-58.

Sharma, Ashish, et al. "Human–AI collaboration enables more empathic conversations in text-based peer-to-peer mental health support." Nature Machine Intelligence 5.1 (2023): 46-57.

Pataranutaporn, Pat, et al. "Influencing human–AI interaction by priming beliefs about AI can increase perceived trustworthiness, empathy and effectiveness." Nature Machine Intelligence 5.10 (2023): 1076-1086.

Steyvers, Mark, et al. "What large language models know and what people think they know." Nature Machine Intelligence (2025): 1-11.

Wang, Angelina, Jamie Morgenstern, and John P. Dickerson. "Large language models that replace human participants can harmfully misportray and flatten identity groups." Nature Machine Intelligence (2025): 1-12.

關(guān)于集智俱樂部讀書會和舉辦方

集智俱樂部讀書會是面向廣大科研工作者的系列論文研讀活動，其目的是共同深入學(xué)習(xí)探討某個科學(xué)議題，了解前沿進展，激發(fā)科研靈感，促進科研合作，降低科研門檻。

讀書會活動始于 2008 年，至今已經(jīng)有 50 余個主題，內(nèi)容涵蓋復(fù)雜系統(tǒng)、人工智能、腦與意識、生命科學(xué)、因果科學(xué)、高階網(wǎng)絡(luò)等。凝聚了眾多優(yōu)秀科研工作者，促進了科研合作發(fā)表論文，孵化了許多科研產(chǎn)品。如：2013 年的“深度學(xué)習(xí)”讀書會孕育了彩云天氣 APP，2015 年的“集體注意力流”讀書會產(chǎn)生了眾包書籍《走近2050》，2020年的開始因果科學(xué)讀書會孕育了全國最大的因果科學(xué)社區(qū)等。

主辦方：集智俱樂部

協(xié)辦方：集智學(xué)園

集智俱樂部成立于 2003 年，是一個從事學(xué)術(shù)研究、享受科學(xué)樂趣的探索者的團體，也是國內(nèi)最早的研究人工智能、復(fù)雜系統(tǒng)的科學(xué)社區(qū)。它倡導(dǎo)以平等開放的態(tài)度、科學(xué)實證的精神，進行跨學(xué)科的研究與交流，力圖搭建一個中國的 “ 沒有圍墻的研究所 ”。集智科學(xué)研究中心（民間非營利企業(yè)）是集智俱樂部的運營主體，其使命為：營造跨學(xué)科探索小生境，催化復(fù)雜性科學(xué)新理論。

集智學(xué)園成立于2016年，是集智俱樂部孕育的創(chuàng)業(yè)團隊。集智學(xué)園致力于傳播復(fù)雜性科學(xué)、人工智能等前沿知識和新興技術(shù)，促進、推動復(fù)雜科學(xué)領(lǐng)域的知識探索與生態(tài)構(gòu)建。