UC San Diego 用奖励训练为 7B 智能体注入心智理论
A new UC San Diego paper builds theory of mind into a 7B agent through its training reward, so the agent learns to read a partner’s beliefs and goals and then r
UC San Diego 新论文通过训练奖励把心智理论（theory of mind）注入 7B 智能体，使其学会推断伙伴的信念与目标，部署时无需额外模型即可独立运行。该方法先用一个模型推断伙伴的信念、意图与想法（包括伙伴如何看待智能体），在 RL 阶段用它为候选回复打分，最终智能体单独运行。论文题为《Mental-Models for Multi-Agent Systems》。
正文
当前显示原文，中文全文译文尚未就绪。
A new UC San Diego paper builds theory of mind into a 7B agent through its training reward, so the agent learns to read a partner’s beliefs and goals and then runs on its own with no extra model at deployment.
LLM agents that negotiate, cooperate or role-play usually guess the other side's goals from prompt text or memory summaries. They keep no explicit estimate of the partner's knowledge or plans, so they can misread intent.
They train a model that infers the partner's beliefs, intents and thoughts, including what the partner thinks of the agent. That model scores candidate replies during RL, and the final agent runs alone without it.
For agents that negotiate or collaborate, train with a reward that judges replies against an inferred model of the partner's goals and beliefs.
– arxiv. org/abs/2610.12453