Learning social norms enhances compatibility in dynamic human-AI coordination

• URL: http://arxiv.org/abs/2607.07021v1
• Date: Wed, 08 Jul 2026 05:39:08 GMT
• Title: Learning social norms enhances compatibility in dynamic human-AI coordination
• Abstract summary: Humans continuously coordinate with others in dynamic interactions, often through implicit, hard-to-quantify social norms.<n>As AI agents become embedded in daily life, they increasingly participate in such interactions and reshape social interaction structures.<n>We identify three principles underlying human social norms: outcome predictability, value alignment, and advantage awareness.
• Score: 22.247716743876214
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Align AI to Dynamic Human-AI Workflows [43.10610450289198]
  We argue for a shift from static and emulative to interactive and complementary alignment.<n>We first formalize this gap by contrasting existing alignment with a trajectory-level view in which human and model behavior co-evolve over time.<n>We argue that human-AI systems amplify these dynamics, introducing new asymmetries that make reasoning about uncertainty harder.
  arXiv  Detail & Related papers  (2026-07-15T18:02:03Z)
• HRIBench: Benchmarking Interaction-Centric Human-Robot Collaboration [62.19372189311434]
  We introduce HRIBench, a diagnostic benchmark for intent-aware human-robot collaboration based on executable scenarios.<n>HRIBench represents collaborative tasks as structured scenario scripts that explicitly model agent roles, temporal dependencies, coordination constraints, and human behavior distributions.<n>Results show that current foundation robot policies struggle substantially in collaborative settings despite strong manipulation ability.
  arXiv  Detail & Related papers  (2026-07-05T09:15:35Z)
• SODE: Analyzing Social Dynamics in LLM Agents [17.885513252130373]
  We introduce SODE (Social Dynamics Evaluation), a framework that evaluates AI agents across three evolutionary dimensions.<n>Applying SODE reveals systematic divergences.<n>We demonstrate that a "long-horizon framing" can unlock reciprocal capabilities in reasoning models.
  arXiv  Detail & Related papers  (2026-05-06T14:50:07Z)
• Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations [80.39504840645687]
  Existing benchmarks measure ToM capability improvement through story-reading, multiple-choice questions from a third-person perspective.<n>This paper proposes a new paradigm of interactive ToM evaluation with both perspective and metric shifts.<n>Our findings reveal that improvements on static benchmarks do not always translate to better performance in dynamic HAI interactions.
  arXiv  Detail & Related papers  (2026-04-28T15:38:31Z)
• MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook [26.126469624250916]
  MoltNet is a large-scale empirical analysis of agent interaction on MoltBook.<n>We examine behavior along four dimensions: intent and motivation, norms and templates, incentives and behavioral drift, emotion and contagion.
  arXiv  Detail & Related papers  (2026-02-13T21:03:59Z)
• Normative Equivalence in Human-AI Cooperation: Behaviour, Not Identity, Drives Cooperation in Mixed-Agent Groups [0.3823356975862005]
  We study how integrating AI agents affects the emergence and maintenance of cooperative norms in small groups.<n>In our sample of 236 participants, we found that reciprocal group dynamics and behavioural inertia primarily drove cooperation.<n>Participants' behaviour followed the same normative logic across human and AI conditions, indicating that cooperation depended on group behaviour rather than partner identity.
  arXiv  Detail & Related papers  (2026-01-28T11:01:09Z)
• Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations [63.80827184637476]
  We introduce D-STAR, a hierarchical policy that disentangles when to act from where to act.<n>We validate our framework through extensive and rigorous simulations.
  arXiv  Detail & Related papers  (2026-01-14T14:37:06Z)
• The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process [13.959658276224266]
  AI alignment with human values and preferences remains a core challenge.<n>As agents engage with one another, they must coordinate to accomplish both individual and collective goals.<n>Social structure can deter or shatter group and individual values.<n>We call on the AI community to treat human, preferential, and objective alignment as an interdependent concept.
  arXiv  Detail & Related papers  (2025-06-01T16:39:43Z)
• The Human Robot Social Interaction (HSRI) Dataset: Benchmarking Foundational Models' Social Reasoning [49.32390524168273]
  Our work aims to advance the social reasoning of embodied artificial intelligence (AI) agents in real-world social interactions.<n>We introduce a large-scale real-world Human Robot Social Interaction (HSRI) dataset to benchmark the capabilities of language models (LMs) and foundational models (FMs)<n>Our dataset consists of 400 real-world human social robot interaction videos and over 10K annotations, detailing the robot's social errors, competencies, rationale, and corrective actions.
  arXiv  Detail & Related papers  (2025-04-07T06:27:02Z)
• Towards interactive evaluations for interaction harms in human-AI systems [8.989911701384788]
  We propose a shift towards evaluation based on textitinteractional ethics, which focuses on textitinteraction harms<n>First, we discuss the limitations of current evaluation methods, which (1) are static, (2) assume a universal user experience, and (3) have limited construct validity.<n>We present practical principles for designing interactive evaluations. These include ecologically valid interaction scenarios, human impact metrics, and diverse human participation approaches.
  arXiv  Detail & Related papers  (2024-05-17T08:49:34Z)
• SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents [107.4138224020773]
  We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and humans. In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We find that GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills.
  arXiv  Detail & Related papers  (2023-10-18T02:27:01Z)
• Training Socially Aligned Language Models on Simulated Social Interactions [99.39979111807388]
  Social alignment in AI systems aims to ensure that these models behave according to established societal values. Current language models (LMs) are trained to rigidly replicate their training corpus in isolation. This work presents a novel training paradigm that permits LMs to learn from simulated social interactions.
  arXiv  Detail & Related papers  (2023-05-26T14:17:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.