Learning social norms enhances compatibility in dynamic human-AI coordination
A study on arXiv shows AI agents often fail in dynamic coordination due to neglecting implicit social norms. From pedestrian-vehicle interaction experiments, researchers identified three principles: outcome predictability, value alignment, and advantage awareness. Incorporating these into LLMs boosted closed-loop task scores nearly fourfold, outperforming human-human interactions by 43%, paving the way for more natural AI integration.
-->
[Submitted on 8 Jul 2026]
Title:Learning social norms enhances compatibility in dynamic human-AI coordination
View a PDF of the paper titled Learning social norms enhances compatibility in dynamic human-AI coordination, by Yi Yang and 6 other authors
View PDF
Abstract:Humans continuously coordinate with others in dynamic interactions, often through implicit, hard-to-quantify social norms that act as shared tacit expectations among interacting agents. As AI agents, including large language models (LLMs), become embedded in daily life, they increasingly participate in such interactions and reshape social interaction structures. Yet they often fail to coordinate with humans in an effective, considerate, and natural manner. We hypothesize that this gap arises because existing approaches align model behavior with human demonstrations without explicitly quantifying the underlying norms that generate such behavior. We selected pedestrian-vehicle interaction as a representative dynamic interaction and developed a simplified experimental platform that captures its key interactive features. From 3,456 dynamic human interactions collected via this platform, we identified three principles underlying human social norms: outcome predictability, value alignment, and advantage awareness. Incorporating these principles into AI agents significantly improves human-AI coordination. In the closed-loop interaction task with humans, the social-norm-informed LLM achieved a nearly fourfold higher total score than the baseline strategy and outperformed human-human interactions by 43%. These findings indicate that formalizing tacit social norms into explicit, quantifiable principles can enable AI agents to achieve mutually beneficial coordination in dynamic interactions, supporting their more natural integration into human society.
Comments: 44 pages, 5 figures, supplementary information included
Subjects:
Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
Cite as: arXiv:2607.07021 [cs.AI]
(or arXiv:2607.07021v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.07021
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yi Yang [view email] [v1] Wed, 8 Jul 2026 05:39:08 UTC (2,427 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Learning social norms enhances compatibility in dynamic human-AI coordination, by Yi Yang and 6 other authors
View PDF
view license
Current browse context:
cs.AI
new | recent | 2026-07
Change to browse by:
cs cs.HC
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
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?)