Metraipolis › archive › dc_87ac000cd021

NormGym: Evaluating Normative Competence through Social Interaction — arXiv:2611.08613

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.08613
License (as archived): CC0-1.0
Archived: 2026-11-09T22:33:37.012Z
SHA-256 of the archived text: af30cafbf7f8d7c1d3966284a28a7f402d5eb4d9cfde4388326bb4077e47c809
Stable URL of this page: https://metraipolis.com/documento/dc_87ac000cd021

How to cite

NormGym: Evaluating Normative Competence through Social Interaction — arXiv:2611.08613 — arXiv (en), https://arxiv.org/abs/2611.08613 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_87ac000cd021 (Metraipolis archive dc_87ac000cd021, sha256 af30cafbf7f8d7c1d3966284a28a7f402d5eb4d9cfde4388326bb4077e47c809)

BibTeX

@misc{dc87ac000cd021,
  title = {NormGym: Evaluating Normative Competence through Social Interaction — arXiv:2611.08613},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08613},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_87ac000cd021; sha256 af30cafbf7f8d7c1d3966284a28a7f402d5eb4d9cfde4388326bb4077e47c809},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08613. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Normative competence, the ability to infer socially enforced expectations from interaction and adjust behavior accordingly, is essential for agents operating in unfamiliar human communities. Yet existing evaluations largely test whether agents can recognize or apply norms they may already know, rather than whether they can acquire previously unknown norms from social interaction. We introduce NormGym, an interactive benchmark for normative competence in which a newcomer must infer a hidden, arbitrary norm while pursuing its own task in a multi-agent community. Success requires distinguishing what is possible from what is permitted, inferring the norm from observed behavior and sanctions, and applying it in new situations. NormGym contains diverse norms and distinct environments, allowing systematic evaluation of current agents, including large language model (LLM) agents. We find that normative competence remains challenging: the strongest evaluated LLM achieves a joint task-and-compliance success rate of 55.3%. Our analysis reveals that models can sometimes revise their behavior following sanctions for their own actions, but struggle to use other agents' behavior and the sanctions they receive to infer the underlying norm. We further find that fine-tuning models may be insufficient to improve normative competence. These results suggest that current models lack a robust, transferable capability for acquiring normative knowledge through social interaction.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.08613 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-09T22:30:47.248Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).