arXiv cs.MA· Anrui Gu, Zhichao Wang, Nicolai Ouporov·· 13 小时前AI 评分39
Fig：自动化多智能体行为诱发系统
Fig: Automated Multiagent Behavior Elicitor
AI 导读
研究团队推出 Fig（Finding Interactions in Games），一个对游戏环境执行定向诱发干预的智能体系统，可将自然语言行为描述拆解为子行为，生成或选择社交游戏，并对游戏引擎、对手、指令和上下文执行单一或组合干预。
正文 · 原文
Abstract:Many social evaluations for multiagent systems study behaviors as they emerge from environments instead of systematically intervening in the environment to elicit such behaviors. We introduce Fig (Finding Interactions in Games), an agentic system that performs targeted elicitation interventions on game environments. It takes a natural language behavior description, decomposes it into sub-behaviors, generates new social games or selects existing ones, and executes single or combined interventions to the games' engine, opponents, instructions, and context. To evaluate model behavior, it combines built-in mechanical checks and synthetic rubric judgments. We validate the interventions, generated games, and evaluation mechanisms via human review. Models attempt the target behavior in 45.2% of episodes on average for valid scenarios generated by Fig for six test behaviors -- cooperation, exploitation, deception, covert coordination, betrayal, and sabotage. For game-behavior pairs with available controls, Fig's interventions increase attempt rates by 10.9% on average compared to matched control games. Fig shows that multiagent environments can serve as programmable test beds for intentional, controllable, and reproducible behavior evaluation. Code is available at this https URL.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.28891 [cs.AI] |
| (or arXiv:2610.28891v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28891 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Anrui Gu [view email]
[v1]
Tue, 20 Oct 2026 20:16:08 UTC (997 KB)
来源：arXiv cs.MA · arxiv.org