Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915799894065152 |
|---|---|
| author | Mumcu, Furkan Yilmaz, Yasin |
| author_facet | Mumcu, Furkan Yilmaz, Yasin |
| contents | Deploying large language model (LLM) agents in shared environments introduces a fundamental tension between individual alignment and collective stability: locally rational decisions can impose negative externalities that degrade system-level performance. We propose Socially-Weighted Alignment (SWA), a game-theoretic framework that modifies inference-time decision making by interpolating between an agent's private objective and an estimate of group welfare via a social weight $λ\in[0,1]$. In a shared-resource congestion game with $n$ agents and congestion severity $β$, we show that SWA induces a critical threshold $λ^*=(n-β)/(n-1)$ above which agents no longer have marginal incentive to increase demand under overload, yielding a phase transition from persistent congestion to stable operation near capacity. We further provide an inference-time algorithmic instantiation of SWA that does not require parameter updates or multi-agent reinforcement learning, and use a multi-agent simulation to empirically validate the predicted threshold behavior. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14471 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems Mumcu, Furkan Yilmaz, Yasin Multiagent Systems Artificial Intelligence Computer Science and Game Theory Machine Learning Deploying large language model (LLM) agents in shared environments introduces a fundamental tension between individual alignment and collective stability: locally rational decisions can impose negative externalities that degrade system-level performance. We propose Socially-Weighted Alignment (SWA), a game-theoretic framework that modifies inference-time decision making by interpolating between an agent's private objective and an estimate of group welfare via a social weight $λ\in[0,1]$. In a shared-resource congestion game with $n$ agents and congestion severity $β$, we show that SWA induces a critical threshold $λ^*=(n-β)/(n-1)$ above which agents no longer have marginal incentive to increase demand under overload, yielding a phase transition from persistent congestion to stable operation near capacity. We further provide an inference-time algorithmic instantiation of SWA that does not require parameter updates or multi-agent reinforcement learning, and use a multi-agent simulation to empirically validate the predicted threshold behavior. |
| title | Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems |
| topic | Multiagent Systems Artificial Intelligence Computer Science and Game Theory Machine Learning |
| url | https://arxiv.org/abs/2602.14471 |