Is There Any Social Principle for LLM-Based Agents?

Focus on Large Language Model based agents should involve more than "human-centered" alignment or application. We argue that more attention should be paid to the agent itself and discuss the potential of establishing tailored social sciences for agents.

cs.CY cs.AI cs.SI Natural Language Processing Techniques Topic Modeling Computer Science

View graph Source

Paper

References (23)

01Influencing human–AI interaction by priming beliefs about AI can increase perceived trustworthiness, empathy and effectivenessPat Pataranutaporn, Ruby Liu, Ed Finn et al.2023 · Nature Machine Intelligence · 174 citations

02The Rise and Potential of Large Language Model Based Agents: A SurveyZhiheng Xi, Wenxiang Chen, Xin Guo et al.2023 · arXiv.org · 2.0k citations In Library

03MetaGPT: Meta Programming for Multi-Agent Collaborative FrameworkSirui Hong, Xiawu Zheng, Jonathan P. Chen et al.2023 · arXiv.org · 2.2k citations In Library

04Deception abilities emerged in large language modelsThilo Hagendorff2023 · Proceedings of the National Academy of Sciences of the United States of America · 179 citations In Library

05S3: Social-network Simulation System with Large Language Model-Empowered AgentsChen Gao, Xiaochong Lan, Zhi-jie Lu et al.2023 · Social Science Research Network · 335 citations In Library

06Enhancing social connectedness with companion robots using AIE. Broadbent, M. Billinghurst, S. G. Boardman et al.2023 · Science Robotics · 31 citations

07ChatGPT broke the Turing test — the race is on for new ways to assess AIC. Biever2023 · Nature · 133 citations

08AI and the transformation of social science researchIgor Grossmann, M. Feinberg, D. C. Parker et al.2023 · Science · 329 citations

09Diplomat: A Dialogue Dataset for Situated Pragmatic ReasoningHengli Li, Songchun Zhu, Zilong Zheng2023 · Neural Information Processing Systems · 21 citations In Library

10Encouraging Divergent Thinking in Large Language Models through Multi-Agent DebateTian Liang, Zhiwei He, Wenxiang Jiao et al.2023 · Conference on Empirical Methods in Natural Language Processing · 1.3k citations In Library

11Heterogeneous Value Alignment Evaluation for Large Language ModelsZhaowei Zhang, N. Liu, Siyuan Qi et al.2023 · Artificial General Intelligence · 6 citations In Library

12Mindstorms in Natural Language-Based Societies of MindMingchen Zhuge, Haozhe Liu, Francesco Faccio et al.2023 · Computational Visual Media · 119 citations In Library

Scroll for more · 11 remaining

Similar papers

LLM-enabled Social AgentsOnder Gurcan, Moharram Challenger2026 · arXiv.org · 0 citations In Library

Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science ResearchJennifer Haase, Sebastian Pokutta2025 · arXiv (Cornell University) · 13 citations In Library

Integrating LLM in Agent-Based Social Simulation: Opportunities and ChallengesP. Taillandier, Jean-Daniel Zucker, A. Grignard et al.2025 · arXiv.org · 10 citations In Library

Practical Considerations for Agentic LLM SystemsChris Sypherd, Vaishak Belle2024 · arXiv (Cornell University) · 15 citations In Library

Evaluating the Use of Large Language Models as Synthetic Social Agents in Social Science ResearchEmma Rose Madden2025 · Journal of Social Computing · 5 citations In Library

Large Language Models can Achieve Social BalancePedro Cisneros-Velarde2024 · arXiv.org · 5 citations In Library

The 1st Workshop on LLM Agents for Social SimulationYige Yuan, Junkai Zhou, Bingbing Xu et al.2025 · International Conference on Information and Knowledge Management · 1 citation In Library

The Emergence of Social Science of Large Language ModelsXiao Jia, Zhanzhan Zhao2025 · arXiv.org · 1 citation In Library

Multi-Agent Language Models: Advancing Cooperation, Coordination, and AdaptationArjun Vaithilingam Sudhakar2025 · arXiv.org · 2 citations In Library

Agentic Large Language Models, a SurveyAske Plaat, Max van Duijn, Bas van Stein et al.2025 · Journal of Artificial Intelligence Research In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal