Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
98 tokens/sec
GPT-4o
61 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
8 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives (2312.11970v1)

Published 19 Dec 2023 in cs.AI, cs.CL, cs.CY, and cs.MA
Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives

Abstract: Agent-based modeling and simulation has evolved as a powerful tool for modeling complex systems, offering insights into emergent behaviors and interactions among diverse agents. Integrating LLMs into agent-based modeling and simulation presents a promising avenue for enhancing simulation capabilities. This paper surveys the landscape of utilizing LLMs in agent-based modeling and simulation, examining their challenges and promising future directions. In this survey, since this is an interdisciplinary field, we first introduce the background of agent-based modeling and simulation and LLM-empowered agents. We then discuss the motivation for applying LLMs to agent-based simulation and systematically analyze the challenges in environment perception, human alignment, action generation, and evaluation. Most importantly, we provide a comprehensive overview of the recent works of LLM-empowered agent-based modeling and simulation in multiple scenarios, which can be divided into four domains: cyber, physical, social, and hybrid, covering simulation of both real-world and virtual environments. Finally, since this area is new and quickly evolving, we discuss the open problems and promising future directions.

PDF HTML Abstract

LLMs Empowered Agent-based Modeling and Simulation: A Survey and Perspectives

Introduction

In the landscape of agent-based modeling and simulation (ABMS), the integration of LLMs presents an innovative approach, enhancing the simulation of complex systems with human-like decision-making processes. This paper surveys the use of LLMs in ABMS across cyber, physical, social, and hybrid domains, elucidating the motivation, challenges, recent advancements, and future directions in this interdisciplinary field.

Background on Agent-based Simulation and LLMs

Agent-based Simulation Concepts

ABMS harnesses the capabilities of agents, simulating their interactions within a defined environment to paper emergent behaviors. Key components of such simulations include:

  • Agents: Individual entities with unique characteristics and decision-making processes.
  • Environment: The context within which agents operate, influencing and being influenced by agent actions.
  • Interaction: The dynamics between agents and between agents and the environment.

The Advent of LLM Empowered Agents

LLMs, with their profound natural language processing abilities, bring about a paradigm shift in ABMS. Their integration into simulations paves the way for simulations that closely mimic human behavior, enhancing the realism and depth of analyses. LLMs contribute significantly in areas of perception, reasoning, adaptive learning, and heterogeneity in agent interactions.

Challenges and Approaches in LLM-based ABMS

Environment Design and Interface

A pivotal step in LLM-based ABMS is environment construction, which can be virtual or real-world. The mechanisms for how agents perceive and interact with these environments predominantly revolve around textual interfaces, leveraging LLMs' natural language prowess. Such designs facilitate intricate simulations encompassing varying domains.

Addressing Human Alignment and Personalization

Aligning LLM agents with human knowledge and ethical values is crucial for realistic simulations. Techniques such as prompt engineering and tuning are employed to cater to domain-specific knowledge and individualized agent characteristics, enhancing the fidelity of the simulations.

Simulating Agent Actions

The paper discusses in depth how planning, memory, and reflection mechanisms are essential for LLM agents to exhibit complex behaviors. These attributes allow agents to strategize actions, recall past experiences, and adapt behaviors based on outcomes, closely aligning with human cognitive processes.

Evaluation Metrics

Evaluating the effectiveness of LLM-based simulations involves assessing the realism and coherence of agent behaviors, as well as adherence to ethical guidelines. Metrics include realness validation, explanatory capabilities of simulated behaviors, and ethical considerations such as bias detection and mitigation.

Recent Work and Domain-specific Advances

The survey presents an exhaustive list of advancements across cyber, physical, social, and hybrid domains. These include simulations for economic systems, social interactions, urban dynamics, and more complex systems that entail intricate interplay between different elements of society and environment.

Open Problems and Future Directions

The paper identifies key areas for future research:

  • Scaling Efficiency: As the scale of simulations expands, computational efficiency becomes paramount. Innovative solutions for model compression and operation optimization are essential.
  • Benchmarking: Establishing comprehensive benchmarks for evaluating LLM-based ABS across various metrics and domains.
  • Open Platforms: The creation of open platforms would democratize access to LLM-based ABS, fostering wider innovation in the field.
  • Robustness and Ethical Considerations: Addressing challenges related to adversarial attacks, out-of-distribution generalization, and mitigating ethical risks inherent in simulating human-like behaviors.

Conclusion

The integration of LLMs into ABMS marks a significant advancement in simulating complex systems with increased realism and depth. This paper highlights the transformative potential of LLM-empowered agents in ABMS, delineating current achievements and charting a course for future research in tackling the outlined challenges. As the field evolves, it promises to offer profound insights into the dynamics of complex systems, from social networks to economic systems, with implications that span across theoretical understanding to practical applications in policy-making and beyond.

File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (245)
  1. Large language models show human-like content biases in transmission chain experiments. Proceedings of the National Academy of Sciences, 120(44):e2313790120, 2023.
  2. Using large language models to simulate multiple humans and replicate human subject studies. In International Conference on Machine Learning, pages 337–371. PMLR, 2023.
  3. Playing repeated games with large language models. arXiv preprint arXiv:2305.16867, 2023.
  4. A survey: agent-based software technology under the eyes of cyber security, security controls, attacks and challenges. International Journal of Advanced Computer Science and Applications (IJACSA), 10(8), 2019.
  5. Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale. In SC22: International Conference for High Performance Computing, Networking, Storage and Analysis, pages 1–15. IEEE, 2022.
  6. Li An. Modeling human decisions in coupled human and natural systems: Review of agent-based models. Ecological modelling, 229:25–36, 2012.
  7. Anonymous. Large language models as rational players in competitive economics games. In Submitted to The Twelfth International Conference on Learning Representations, 2023. under review.
  8. Anonymous. Rethinking the buyer’s inspection paradox in information markets with language agents. In Submitted to The Twelfth International Conference on Learning Representations, 2023. under review.
  9. Discrete choice models of pedestrian walking behavior. Transportation Research Part B: Methodological, 40(8):667–687, 2006.
  10. Out of one, many: Using language models to simulate human samples. Political Analysis, 31(3):337–351, 2023.
  11. Have llms advanced enough? a challenging problem solving benchmark for large language models. arXiv preprint arXiv:2305.15074, 2023.
  12. Spatiotemporal simulation of urban growth patterns using agent-based modeling: The case of tehran. Cities, 32:33–42, 2013.
  13. W Brian Arthur. Designing economic agents that act like human agents: A behavioral approach to bounded rationality. The American economic review, 81(2):353–359, 1991.
  14. Anonymous Authors. Sociodojo: Building lifelong analytical agents.
  15. Agent based models and opinion dynamics as markov chains. Social Networks, 34(4):549–561, 2012.
  16. Simulation of multi-agent manufacturing systems using agent-based modelling platforms. In 2011 9th IEEE International Conference on Industrial Informatics, pages 477–482. IEEE, 2011.
  17. Applications of agent-based modeling and simulation to healthcare operations management. In Handbook of healthcare operations management: methods and applications, pages 45–74. Springer, 2013.
  18. Joana Xavier Barros. Urban Growth in Latin American Cities-Exploring urban dynamics through agent-based simulation. University of London, University College London (United Kingdom), 2004.
  19. Complexworld: A large language model-based interactive fiction learning environment for text-based reinforcement learning agents. In International Joint Conference on Artificial Intelligence, 2023.
  20. Michael Batty. Agent-based pedestrian modelling. 2003.
  21. Decoding gpt’s hidden ‘rationality’of cooperation. 2023.
  22. Comparing methods of targeting obesity interventions in populations: an agent-based simulation. SSM-population health, 3:211–218, 2017.
  23. Jerome R Bellegarda. Statistical language model adaptation: review and perspectives. Speech communication, 42(1):93–108, 2004.
  24. An agent-based bioenergetics model for predicting impacts of environmental change on a top marine predator, the weddell seal. Ecological Modelling, 351:36–50, 2017.
  25. Using cognitive psychology to understand gpt-3. Proceedings of the National Academy of Sciences, 120(6):e2218523120, 2023.
  26. The effects of market network heterogeneity on innovation diffusion: An agent-based modeling approach. Journal of Product Innovation Management, 27(5):741–760, 2010.
  27. Emergent autonomous scientific research capabilities of large language models. arXiv preprint arXiv:2304.05332, 2023.
  28. Simulation and validation of a reinforcement learning agent-based model for multi-stakeholder forest management. Computers, Environment and Urban Systems, 34(2):162–174, 2010.
  29. Chemcrow: Augmenting large-language models with chemistry tools. arXiv preprint arXiv:2304.05376, 2023.
  30. Effects of heterogeneity in residential preferences on an agent-based model of urban sprawl. Ecology and society, 11(1), 2006.
  31. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
  32. Leland Bybee. Surveying generative ai’s economic expectations. arXiv preprint arXiv:2305.02823, 2023.
  33. Optimization of healthcare emergency departments by agent-based simulation. Procedia computer science, 4:1880–1889, 2011.
  34. The role of complexity for digital twins of cities. Nature Computational Science, pages 1–8, 2023.
  35. Grounding large language models in interactive environments with online reinforcement learning. arXiv preprint arXiv:2302.02662, 2023.
  36. Chateval: Towards better llm-based evaluators through multi-agent debate. arXiv preprint arXiv:2308.07201, 2023.
  37. A survey on evaluation of large language models. arXiv preprint arXiv:2307.03109, 2023.
  38. From text to mitre techniques: Exploring the malicious use of large language models for generating cyber attack payloads. arXiv preprint arXiv:2305.15336, 2023.
  39. Jailbreaker in jail: Moving target defense for large language models. arXiv preprint arXiv:2310.02417, 2023.
  40. Open-vocabulary queryable scene representations for real world planning. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 11509–11522. IEEE, 2023.
  41. Put your money where your mouth is: Evaluating strategic planning and execution of llm agents in an auction arena. arXiv preprint arXiv:2310.05746, 2023.
  42. Liang Chen. Agent-based modeling in urban and architectural research: A brief literature review. Frontiers of Architectural Research, 1(2):166–177, 2012.
  43. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. arXiv preprint arXiv:2308.10848, 2023.
  44. The emergence of economic rationality of gpt. arXiv preprint arXiv:2305.12763, 2023.
  45. Compost: Characterizing and evaluating caricature in llm simulations. arXiv preprint arXiv:2310.11501, 2023.
  46. Batch prompting: Efficient inference with large language model apis. arXiv preprint arXiv:2301.08721, 2023.
  47. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, 24(240):1–113, 2023.
  48. Simulation of an agent based system behavior in a dynamic and unpredicted environment. Simulation, 1(4):172–176, 2011.
  49. On agent-based modeling and computational social science. Frontiers in psychology, 5:668, 2014.
  50. A definition, benchmark and database of ai for social good initiatives. Nature Machine Intelligence, 3(2):111–115, 2021.
  51. Drive as you speak: Enabling human-like interaction with large language models in autonomous vehicles. arXiv preprint arXiv:2309.10228, 2023.
  52. Kahneman Daniel. Thinking, fast and slow. 2017.
  53. Mesoscopic traffic flow model for agent-based simulation. Procedia Computer Science, 151:858–863, 2019.
  54. Emergent cooperation and strategy adaptation in multi-agent systems: An extended coevolutionary theory with llms. Electronics, 12(12):2722, 2023.
  55. Google DeepMind. Introducing gemini: our largest and most capable ai model. https://blog.google/technology/ai/google-gemini-ai, 12 2023. (Accessed on 07/12/2023).
  56. Hiroshi Deguchi. Economics as an agent-based complex system: toward agent-based social systems sciences. Springer Science & Business Media, 2011.
  57. Mind2web: Towards a generalist agent for the web. arXiv preprint arXiv:2306.06070, 2023.
  58. Toxicity in chatgpt: Analyzing persona-assigned language models. arXiv preprint arXiv:2304.05335, 2023.
  59. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018.
  60. A survey for in-context learning. arXiv preprint arXiv:2301.00234, 2022.
  61. Alpacafarm: A simulation framework for methods that learn from human feedback. arXiv preprint arXiv:2305.14387, 2023.
  62. Benchmarking graph neural networks. Journal of Machine Learning Research, 24(43):1–48, 2023.
  63. Social network analysis and agent-based modeling in social epidemiology. Epidemiologic Perspectives & Innovations, 9(1):1–9, 2012.
  64. Exploring cooperation and competition using agent-based modeling. Proceedings of the National Academy of Sciences, 99(suppl_3):7193–7194, 2002.
  65. Agent-based modelling. Modelling norms, pages 65–84, 2014.
  66. Chatgpt outperforms humans in emotional awareness evaluations. Frontiers in Psychology, 14:1199058, 2023.
  67. Human-level play in the game of diplomacy by combining language models with strategic reasoning. Science, 378(6624):1067–1074, 2022.
  68. Miguel Faria-e Castro and Fernando Leibovici. Artificial intelligence and inflation forecasts. Technical report, 2023.
  69. Learning to simulate human mobility. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pages 3426–3433, 2020.
  70. Linking agent-based models and stochastic models of financial markets. Proceedings of the National Academy of Sciences, 109(22):8388–8393, 2012.
  71. On the creativity of large language models. arXiv preprint arXiv:2304.00008, 2023.
  72. Drive like a human: Rethinking autonomous driving with large language models. arXiv preprint arXiv:2307.07162, 2023.
  73. S3: Social-network simulation system with large language model-empowered agents. arXiv preprint arXiv:2307.14984, 2023.
  74. Macroeconomics from the Bottom-up, volume 1. Springer Science & Business Media, 2011.
  75. Impact of urban planning on household’s residential decisions: An agent-based simulation model for vienna. Environmental Modelling & Software, 45:92–103, 2013.
  76. Chatgpt has aced the test of understanding in college economics: Now what? The American Economist, page 05694345231169654, 2023.
  77. Nigel Gilbert. Agent-based social simulation: dealing with complexity. The Complex Systems Network of Excellence, 9(25):1–14, 2004.
  78. Nigel Gilbert. Computational social science: Agent-based social simulation. In Agent-based modelling and simulation, pages 115–134. Bardwell, 2007.
  79. How to build and use agent-based models in social science. Mind & Society, 1:57–72, 2000.
  80. Simulation for the social scientist. McGraw-Hill Education (UK), 2005.
  81. Fulin Guo. Gpt agents in game theory experiments. arXiv preprint arXiv:2305.05516, 2023.
  82. Suspicion-agent: Playing imperfect information games with theory of mind aware gpt-4. arXiv preprint arXiv:2309.17277, 2023.
  83. A real-world webagent with planning, long context understanding, and program synthesis. arXiv preprint arXiv:2307.12856, 2023.
  84. Language models represent space and time. arXiv preprint arXiv:2310.02207, 2023.
  85. Agent-based participatory simulations: Merging multi-agent systems and role-playing games. Journal of artificial societies and social simulation, 9(4), 2006.
  86. Human-like intuitive behavior and reasoning biases emerged in large language models but disappeared in chatgpt. Nature Computational Science, pages 1–6, 2023.
  87. Evaluating large language models in generating synthetic hci research data: a case study. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, pages 1–19, 2023.
  88. Agent-based modelling in economics. John Wiley & Sons, 2015.
  89. " guinea pig trials" utilizing gpt: A novel smart agent-based modeling approach for studying firm competition and collusion. arXiv preprint arXiv:2308.10974, 2023.
  90. The faculty of language: what is it, who has it, and how did it evolve? science, 298(5598):1569–1579, 2002.
  91. Agent-based modeling in ecological economics. Annals of the New York Academy of Sciences, 1185(1):39–53, 2010.
  92. Dirk Helbing. Social self-organization: Agent-based simulations and experiments to study emergent social behavior. Springer, 2012.
  93. Social force model for pedestrian dynamics. Physical review E, 51(5):4282, 1995.
  94. Computer models solving intelligence test problems: Progress and implications. Artificial Intelligence, 230:74–107, 2016.
  95. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 2023.
  96. John J Horton. Large language models as simulated economic agents: What can we learn from homo silicus? Technical report, National Bureau of Economic Research, 2023.
  97. Iq of neural networks. arXiv preprint arXiv:1710.01692, 2017.
  98. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021.
  99. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems, 33:22118–22133, 2020.
  100. War and peace (waragent): Large language model-based multi-agent simulation of world wars. arXiv preprint arXiv:2311.17227, 2023.
  101. Benchmarking large language models as ai research agents. arXiv preprint arXiv:2310.03302, 2023.
  102. Personalized soups: Personalized large language model alignment via post-hoc parameter merging. arXiv preprint arXiv:2310.11564, 2023.
  103. Health system-scale language models are all-purpose prediction engines. Nature, pages 1–6, 2023.
  104. Surrealdriver: Designing generative driver agent simulation framework in urban contexts based on large language model. arXiv preprint arXiv:2309.13193, 2023.
  105. Cgmi: Configurable general multi-agent interaction framework. arXiv preprint arXiv:2308.12503, 2023.
  106. Fairness as a constraint on profit seeking: Entitlements in the market. The American economic review, pages 728–741, 1986.
  107. Big data, agents, and machine learning: towards a data-driven agent-based modeling approach. In Proceedings of the Annual Simulation Symposium, pages 1–12, 2018.
  108. Automatic calibration of dynamic and heterogeneous parameters in agent-based models. Autonomous Agents and Multi-Agent Systems, 35(2):46, 2021.
  109. Ai-augmented surveys: Leveraging large language models for opinion prediction in nationally representative surveys. arXiv preprint arXiv:2305.09620, 2023.
  110. An agent-based crowd behaviour model for real time crowd behaviour simulation. Pattern Recognition Letters, 44:30–38, 2014.
  111. The socialai school: Insights from developmental psychology towards artificial socio-cultural agents. arXiv preprint arXiv:2307.07871, 2023.
  112. Certifying llm safety against adversarial prompting. arXiv preprint arXiv:2309.02705, 2023.
  113. Stance detection with collaborative role-infused llm-based agents. arXiv preprint arXiv:2310.10467, 2023.
  114. Matthias Lengnick. Agent-based macroeconomics: A baseline model. Journal of Economic Behavior & Organization, 86:102–120, 2013.
  115. Why are economists sceptical about agent-based simulations? Physica A: Statistical Mechanics and its Applications, 355(1):103–109, 2005.
  116. Seed-bench: Benchmarking multimodal llms with generative comprehension. arXiv preprint arXiv:2307.16125, 2023.
  117. Quantifying the impact of large language models on collective opinion dynamics. arXiv preprint arXiv:2308.03313, 2023.
  118. Modelscope-agent: Building your customizable agent system with open-source large language models. arXiv preprint arXiv:2309.00986, 2023.
  119. Camel: Communicative agents for" mind" exploration of large scale language model society. arXiv preprint arXiv:2303.17760, 2023.
  120. Opinion dynamics model based on the cognitive dissonance: An agent-based simulation. Information Fusion, 56:1–14, 2020.
  121. Large language model-empowered agents for simulating macroeconomic activities. arXiv preprint arXiv:2310.10436, 2023.
  122. Are you in a masquerade? exploring the behavior and impact of large language model driven social bots in online social networks. arXiv preprint arXiv:2307.10337, 2023.
  123. Is gpt-3 a psychopath? evaluating large language models from a psychological perspective. arXiv preprint arXiv:2212.10529, 2022.
  124. Encouraging divergent thinking in large language models through multi-agent debate. arXiv preprint arXiv:2305.19118, 2023.
  125. Agentsims: An open-source sandbox for large language model evaluation. arXiv preprint arXiv:2308.04026, 2023.
  126. Long-Ji Lin. Self-improving reactive agents based on reinforcement learning, planning and teaching. Machine learning, 8:293–321, 1992.
  127. Using agent-based modelling to simulate social-ecological systems across scales. GeoInformatica, 23:269–298, 2019.
  128. Training socially aligned language models in simulated human society. arXiv preprint arXiv:2305.16960, 2023.
  129. Agentbench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688, 2023.
  130. How well do machines perform on iq tests: a comparison study on a large-scale dataset. In IJCAI, pages 6110–6116, 2019.
  131. Microscopic traffic simulation using sumo. In 2018 21st international conference on intelligent transportation systems (ITSC), pages 2575–2582. IEEE, 2018.
  132. Self: Language-driven self-evolution for large language model. arXiv preprint arXiv:2310.00533, 2023.
  133. Agent-based human behavior modeling for crowd simulation. Computer Animation and Virtual Worlds, 19(3-4):271–281, 2008.
  134. Agent-based simulation of residential promoting policy effects on downtown revitalization. Journal of Artificial Societies and Social Simulation, 16(2):2, 2013.
  135. Tutorial on agent-based modeling and simulation. In Proceedings of the Winter Simulation Conference, 2005., pages 14–pp. IEEE, 2005.
  136. From factors to actors: Computational sociology and agent-based modeling. Annual review of sociology, 28(1):143–166, 2002.
  137. Agent-based modeling and simulation of collaborative social networks. 2003.
  138. Understanding urban mobility and the impact of public policies: The role of the agent-based models. Research in Transportation Economics, 55:50–59, 2016.
  139. Deepiq: A human-inspired ai system for solving iq test problems. In 2019 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE, 2019.
  140. Geollm: Extracting geospatial knowledge from large language models. arXiv preprint arXiv:2310.06213, 2023.
  141. Alympics: Language agents meet game theory. arXiv preprint arXiv:2311.03220, 2023.
  142. Distributed agent-based traffic simulations. IEEE Intelligent Transportation Systems Magazine, 10(1):145–156, 2018.
  143. The role of agent-based models in wildlife ecology and management. Ecological modelling, 222(8):1544–1556, 2011.
  144. On the state of the art of evaluation in neural language models. arXiv preprint arXiv:1707.05589, 2017.
  145. Economic behaviour and agent-based modelling. In Routledge handbook of behavioral economics, pages 405–415. Routledge, 2016.
  146. Welfare diplomacy: Benchmarking language model cooperation. arXiv preprint arXiv:2310.08901, 2023.
  147. Self-adaptive large language model (llm)-based multiagent systems. arXiv preprint arXiv:2307.06187, 2023.
  148. Open science by design: Realizing a vision for 21st century research. 2018.
  149. OpenAI. Introducing chatgpt. https://openai.com/blog/chatgpt, 2022. (Accessed on 01/12/2023).
  150. Policy-focused agent-based modeling using rl behavioral models. arXiv preprint arXiv:2006.05048, 2020.
  151. Choicemates: Supporting unfamiliar online decision-making with multi-agent conversational interactions. arXiv preprint arXiv:2310.01331, 2023.
  152. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22, 2023.
  153. Social simulacra: Creating populated prototypes for social computing systems. In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, pages 1–18, 2022.
  154. Multi-agent reinforcement learning with approximate model learning for competitive games. PloS one, 14(9):e0222215, 2019.
  155. Agent-based simulation of value flow in an industrial production process. Processes, 7(2):82, 2019.
  156. Agent-based simulation of ecological models. In Agent-Based Simulation, 2004.
  157. An agent-based approach for modeling dynamics of contagious disease spread. International journal of health geographics, 8(1):1–17, 2009.
  158. Impact assessment predicted by means of genetic agent-based modeling. Critical reviews in toxicology, 34(6):487–498, 2004.
  159. Investigating emergent goal-like behaviour in large language models using experimental economics. arXiv preprint arXiv:2305.07970, 2023.
  160. A survey on agent-based modelling assisted by machine learning. Expert Systems, page e13325, 2023.
  161. Potential gnp: Its measurement and significance: A dissenting opinion. In Carnegie-Rochester Conference Series on Public Policy, volume 10, pages 179–186. Elsevier, 1979.
  162. Modelling bounded rationality in organizations: Progress and prospects. Academy of Management Annals, 9(1):337–392, 2015.
  163. Communicative agents for software development. arXiv preprint arXiv:2307.07924, 2023.
  164. Tool learning with foundation models. arXiv preprint arXiv:2304.08354, 2023.
  165. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.
  166. Agent-based modeling and simulation of an autonomic manufacturing execution system. Computers in industry, 63(1):53–78, 2012.
  167. Juliette Rouchier. Agent-based simulation as a useful tool for the study of markets. Simulating Social Complexity: A Handbook, pages 671–704, 2017.
  168. Imagenet large scale visual recognition challenge. International journal of computer vision, 115:211–252, 2015.
  169. Agent-based models of financial markets. Reports on Progress in Physics, 70(3):409, 2007.
  170. Status quo bias in decision making. Journal of risk and uncertainty, 1:7–59, 1988.
  171. Toolformer: Language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761, 2023.
  172. Emergent structures in supply chains-a study integrating agent-based and system dynamics modeling. In 36th Annual Hawaii International Conference on System Sciences, 2003. Proceedings of the, pages 9–pp. IEEE, 2003.
  173. Creating a large language model of a philosopher. arXiv preprint arXiv:2302.01339, 2023.
  174. Segregation dynamics with reinforcement learning and agent based modeling. Scientific reports, 10(1):11771, 2020.
  175. Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action. In Conference on Robot Learning, pages 492–504. PMLR, 2023.
  176. Gnm: A general navigation model to drive any robot. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 7226–7233. IEEE, 2023.
  177. Rehearsal: Simulating conflict to teach conflict resolution. arXiv preprint arXiv:2309.12309, 2023.
  178. Role play with large language models. Nature, pages 1–6, 2023.
  179. Towards out-of-distribution generalization: A survey. arXiv preprint arXiv:2108.13624, 2021.
  180. High-throughput generative inference of large language models with a single gpu. arXiv preprint arXiv:2303.06865, 2023.
  181. Reflexion: Language agents with verbal reinforcement learning. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  182. Alfworld: Aligning text and embodied environments for interactive learning. arXiv preprint arXiv:2010.03768, 2020.
  183. Covid-abs: An agent-based model of covid-19 epidemic to simulate health and economic effects of social distancing interventions. Chaos, Solitons & Fractals, 139:110088, 2020.
  184. A systems approach to healthcare: agent-based modeling, community mental health, and population well-being. Artificial intelligence in medicine, 63(2):61–71, 2015.
  185. Herbert Alexander Simon. Models of bounded rationality: Empirically grounded economic reason, volume 3. MIT press, 1997.
  186. Mind meets machine: Unravelling gpt-4’s cognitive psychology. arXiv preprint arXiv:2303.11436, 2023.
  187. Large language models encode clinical knowledge. Nature, 620(7972):172–180, 2023.
  188. Llm-planner: Few-shot grounded planning for embodied agents with large language models. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2998–3009, 2023.
  189. Adaplanner: Adaptive planning from feedback with language models. arXiv preprint arXiv:2305.16653, 2023.
  190. James Surowiecki. The wisdom of crowds. Anchor, 2005.
  191. An evolutionary model of personality traits related to cooperative behavior using a large language model. arXiv preprint arXiv:2310.05976, 2023.
  192. Stanford alpaca: An instruction-following llama model. https://github.com/tatsu-lab/stanford_alpaca, 2023.
  193. AutoGPT Team. Autogpt: the heart of the open-source agent ecosystem. https://github.com/Significant-Gravitas/AutoGPT, 2022. (Accessed on 01/10/2023).
  194. XAgent Team. Xagent: An autonomous agent for complex task solving, 2023.
  195. Pietro Terna et al. Simulation tools for social scientists: Building agent based models with swarm. Journal of artificial societies and social simulation, 1(2):1–12, 1998.
  196. Large language models in medicine. Nature medicine, 29(8):1930–1940, 2023.
  197. Evil geniuses: Delving into the safety of llm-based agents. arXiv preprint arXiv:2311.11855, 2023.
  198. Michael Tomasello. Origins of human communication. MIT press, 2010.
  199. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
  200. Large language models still can’t plan (a benchmark for llms on planning and reasoning about change). arXiv preprint arXiv:2206.10498, 2022.
  201. Clemens Van Dinther. Agent-based simulation for research in economics. In Handbook on information technology in finance, pages 421–442. Springer, 2008.
  202. Minimum levels of interpretability for artificial moral agents. arXiv preprint arXiv:2307.00660, 2023.
  203. Friederike Wall. Agent-based modeling in managerial science: an illustrative survey and study. Review of Managerial Science, 10(1):135–193, 2016.
  204. Glue: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461, 2018.
  205. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291, 2023.
  206. On the robustness of chatgpt: An adversarial and out-of-distribution perspective. arXiv preprint arXiv:2302.12095, 2023.
  207. Agent-based models in financial market studies. In Journal of Physics: Conference Series, volume 1039, page 012022. IOP Publishing, 2018.
  208. A survey on large language model based autonomous agents. arXiv preprint arXiv:2308.11432, 2023.
  209. Recagent: A novel simulation paradigm for recommender systems. arXiv preprint arXiv:2306.02552, 2023.
  210. Unleashing cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration. arXiv preprint arXiv:2307.05300, 2023.
  211. Humanoid agents: Platform for simulating human-like generative agents. arXiv preprint arXiv:2310.05418, 2023.
  212. Steven Weber. The success of open source. Harvard University Press, 2004.
  213. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837, 2022.
  214. Agent-based modeling of policies to improve urban food access for low-income populations. Applied Geography, 40:1–10, 2013.
  215. Epidemic modeling with generative agents. arXiv preprint arXiv:2307.04986, 2023.
  216. Stephen Wolfram. Cellular automata as models of complexity. Nature, 311(5985):419–424, 1984.
  217. Intelligent agents: Theory and practice. The knowledge engineering review, 10(2):115–152, 1995.
  218. Plan, eliminate, and track–language models are good teachers for embodied agents. arXiv preprint arXiv:2305.02412, 2023.
  219. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864, 2023.
  220. The wall street neophyte: A zero-shot analysis of chatgpt over multimodal stock movement prediction challenges. arXiv preprint arXiv:2304.05351, 2023.
  221. Urban generative intelligence (ugi): A foundational platform for embodied agent and future city. arXiv preprint, 2023.
  222. Exploring large language models for communication games: An empirical study on werewolf. arXiv preprint arXiv:2309.04658, 2023.
  223. From instructions to intrinsic human values–a survey of alignment goals for big models. arXiv preprint arXiv:2308.12014, 2023.
  224. Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601, 2023.
  225. Unpacking the ethical value alignment in big models. arXiv preprint arXiv:2310.17551, 2023.
  226. Yoheinakajima. Babyagi. https://github.com/yoheinakajima/babyagi, 2023. (Accessed on 01/10/2023).
  227. Glm-130b: An open bilingual pre-trained model. In The Eleventh International Conference on Learning Representations, 2023.
  228. On generative agents in recommendation. arXiv preprint arXiv:2310.10108, 2023.
  229. Bo Zhang and Donald L DeAngelis. An overview of agent-based models in plant biology and ecology. Annals of Botany, 126(4):539–557, 2020.
  230. Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485, 2023.
  231. Exploring collaboration mechanisms for llm agents: A social psychology view. arXiv preprint arXiv:2310.02124, 2023.
  232. Benchmarking large language models for news summarization. arXiv preprint arXiv:2301.13848, 2023.
  233. Explainability for large language models: A survey. arXiv preprint arXiv:2309.01029, 2023.
  234. Competeai: Understanding the competition behaviors in large language model-based agents. arXiv preprint arXiv:2310.17512, 2023.
  235. A survey of large language models. arXiv preprint arXiv:2303.18223, 2023.
  236. The ai economist: Taxation policy design via two-level deep multiagent reinforcement learning. Science advances, 8(18):eabk2607, 2022.
  237. Webarena: A realistic web environment for building autonomous agents. arXiv preprint arXiv:2307.13854, 2023.
  238. Sotopia: Interactive evaluation for social intelligence in language agents. arXiv preprint arXiv:2310.11667, 2023.
  239. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592, 2023.
  240. Promptbench: Towards evaluating the robustness of large language models on adversarial prompts. arXiv preprint arXiv:2306.04528, 2023.
  241. Ghost in the minecraft: Generally capable agents for open-world enviroments via large language models with text-based knowledge and memory. arXiv preprint arXiv:2305.17144, 2023.
  242. A survey on model compression for large language models. arXiv preprint arXiv:2308.07633, 2023.
  243. Mindstorms in natural language-based societies of mind. arXiv preprint arXiv:2305.17066, 2023.
  244. Exploring ai ethics of chatgpt: A diagnostic analysis. arXiv preprint arXiv:2301.12867, 2023.
  245. Wireless multi-agent generative ai: From connected intelligence to collective intelligence. arXiv preprint arXiv:2307.02757, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. Chen Gao (136 papers)
  2. Xiaochong Lan (12 papers)
  3. Nian Li (59 papers)
  4. Yuan Yuan (234 papers)
  5. Jingtao Ding (50 papers)
  6. Zhilun Zhou (8 papers)
  7. Fengli Xu (47 papers)
  8. Yong Li (628 papers)
Citations (51)
View on Semantic Scholar