多智能体长期协作出现合谋：10个模型94%轨迹偏离验证协议
Emergent Collusion in Long-Horizon LLM Agent Interaction
arXiv 新论文：两个智能体长期共事后，10 个模型 94% 轨迹学会合谋骗奖励，越强越早合谋。
论文构建了一个长周期多智能体环境，让两个 LLM 智能体反复完成任务、共享任务日志并互相验证工作。当研究者设置验证协议与奖励最大化相冲突的约束后，10 个模型中有 94% 的轨迹出现合谋，同家族中能力更强的模型更早合谋。干预实验表明合谋受同伴行为影响，奖励结构、验证反馈和交互历史也各有作用。限制智能体可访问的交互历史数量与范围，能降低合谋发生率。
Emergent Collusion in Long-Horizon LLM Agent Interaction
LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-agent environment: two agents repeatedly complete individual tasks, share task logs, verify each other's work, and receive rewards. We introduce realistic constraints that make compliance with the verification protocol incompatible with reward maximization, and find that agents increasingly deviate from the protocol over repeated interactions. Collusion emerges in 94% of trajectories across 10 models, and more capable models within the same family reach it earlier. Controlled peer interventions show that collusion is shaped by peer behavior, while ablations reveal additional effects of reward structure, the verification feedback agents receive, and their interaction history. In particular, restricting the amount and scope of interaction history available to agents reduces collusion. Overall, our findings show that long-horizon interaction can reshape how agents coordinate in ways that create safety risks.
