社交智能大语言模型智能体中意图的概率建模
Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents
AI总结：
针对多轮社交对话中LLM智能体的意图感知问题，提出基于信念分布动态更新的概率意图建模框架，在SOTOPIA环境中较基线取得显著提升，甚至略优于直接观测意图的预言机智能体，为社交智能LLM智能体研发提供新思路。
摘要：
我们提出了一种适用于多轮社交对话场景下大语言模型（LLM）智能体的概率意图建模框架。该框架维护对话伙伴潜在意图上的信念分布，先基于上下文先验信息初始化，并在每轮对话后通过似然估计动态更新。不断演化的分布为策略提供了额外的上下文支撑，使智能体能够在不确定性下采用自适应对话策略。在SOTOPIA（社交智能体交互评估环境）中开展的初步实验显示出一致的性能提升：与Qwen2.5-7B基线相比，所提框架在SOTOPIA-All上的总体得分提升9.0%，在SOTOPIA-Hard上提升4.1%，且略微优于可直接观测对话伙伴意图的预言机智能体。这些早期结果表明，概率意图建模能够为社交智能LLM智能体的发展提供助力。
英文摘要：
We present a probabilistic intent modeling framework for large language model (LLM) agents in multi-turn social dialogue. The framework maintains a belief distribution over a partner's latent intentions, initialized from contextual priors and dynamically updated through likelihood estimation after each utterance. The evolving distribution provides additional contextual grounding for the policy, enabling adaptive dialogue strategies under uncertainty. Preliminary experiments in the SOTOPIA environment show consistent improvements: the proposed framework increases the Overall score by 9.0% on SOTOPIA-All and 4.1% on SOTOPIA-Hard compared with the Qwen2.5-7B baseline, and slightly surpasses an oracle agent that directly observes partner intentions. These early results suggest that probabilistic intent modeling can contribute to the development of socially intelligent LLM agents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
