智能体
arxiv.org ·
行为还不够：基于机制的大语言模型社会中社会规范涌现评估
该论文指出仅凭行为收敛无法判定社会规范涌现，因为相同的合作均衡可能来自共同期望、策略激励或单纯模仿。作者提出评估框架，在行为收敛之外测量智能体的经验性与规范性期望，并通过受控消融分离社会学习（互动）与社会选择（网络分组）两种机制，在四个 LLM 家族下检验对抗扰动后的稳定性。结果显示：引出期望会提高合作贡献，社会学习稳定行为，社会选择能可靠识别合作者但行为强化有限；扰动后规范性期望与行为协调的恢复方式不同。该框架使各机制贡献可被分别归因，为多智能体系统设计者选择维持合作的社会过程提供依据。
AI推荐理由 arXiv 多智能体系统方向新论文，提出基于机制的评估框架：除行为收敛外，还测量智能体的经验性与规范性期望，并通过受控消融分离社会学习（互动）与社会选择（网络分组）两种机制，在四个 LLM 家族下测试对抗扰动后的稳定性。结论指出期望引出会提升合作贡献、社会学习稳定行为、社会选择能识别合作者但行为强化有限，且扰动后规范性期望与行为协调的恢复路径不同。局限是仅基于摘要，未见实验规模、模型版本与量化指标，结论为受控实验条件下的初步发现。
72
正文
Computer Science > Multiagent Systems
arXiv:2609.26481 (cs)
[Submitted on 22 Sep 2026]
Title:Behavior is Not Enough: A Mechanism-Based Evaluation of Social Norm Emergence in LLM Societies
Authors:Rasika Muralidharan, Haewoon Kwak, Jisun An
View a PDF of the paper titled Behavior is Not Enough: A Mechanism-Based Evaluation of Social Norm Emergence in LLM Societies, by Rasika Muralidharan and 2 other authors
View PDF
HTML (experimental)
Abstract:Social norms cannot be identified from behavior alone: the same cooperative equilibrium may reflect shared expectations, strategic incentives, or simple imitation. Yet in multi-agent large language model systems, prior work largely treats behavioral convergence as evidence of norm emergence. In this work, we introduce an evaluation framework that measures agents' reported empirical and normative expectations in addition to behavioral convergence. Through controlled ablations, we test the effect of expectation elicitation and isolate two collective mechanisms central to theories of norm formation---social learning through interaction and social selection through network-based group formation. We further test the stability of these resulting dynamics under adversarial disruption across four LLM families. We find that eliciting expectations increases cooperative contributions, while social learning stabilizes behavior, and social selection reliably identifies cooperators but provides limited behavioral reinforcement. Following disruption, normative expectations and behavioral coordination recover differently. Together, these results show that similar cooperative outcomes can arise from different underlying social processes. By making expectations observable, our framework allows us to attribute each mechanism's contribution separately, offering designers of multi-agent systems a principled basis for selecting the social processes that sustain cooperation.
Comments:
Subjects:
Multiagent Systems (cs.MA); Computation and Language (cs.CL); Computers and Society (cs.CY); Computer Science and Game Theory (cs.GT); Social and Information Networks (cs.SI)
Cite as:
arXiv:2609.26481 [cs.MA]
(or
arXiv:2609.26481v1 [cs.MA] for this version)
https://doi.org/10.48550/arXiv.2609.26481
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Rasika Muralidharan [view email]
[v1]
Tue, 22 Sep 2026 14:21:04 UTC (1,289 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Behavior is Not Enough: A Mechanism-Based Evaluation of Social Norm Emergence in LLM Societies, by Rasika Muralidharan and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.MA
new
|
recent
| 2026-09
Change to browse by:
cs
cs.CL
cs.CY
cs.GT
cs.SI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)