Evaluating Generative Agents with Actions Grounded in Socially Distributed Task Environments using Incognita

본문 미리보기

arXiv:2607.02975v1 Announce Type: new Abstract: Effective agency in social environments depends on when an agent seeks knowledge, when it acts, and whether its actions are justified by acquired information. Existing grounded benchmarks provide executable actions, persistent state, and verifiable outcomes, while social simulation environments provide rich interaction among language agents. We study an evaluation setting that combines these requirements. We define socially distributed task enviro