用概率模型追踪对话伙伴的隐含意图，让AI更懂人心。
Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents
- 基于上下文先验动态更新对方意图的概率分布
- 在SOTOPIA测试中整体得分提升9.0%，困难场景提升4.1%
- 适合开发能理解社交意图的智能对话系统
我们提出一种用于多轮社交对话中大语言模型（LLM）代理的概率意图建模框架。该框架维护对对话伙伴潜在意图的信念分布，初始值来自上下文先验，并在每次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额外上下文支持，使代理能在不确定性下自适应调整对话策略。初步实验在SOTOPIA环境中显示：与Qwen2.5-7B基线相比，该框架在SOTOPIA-All上整体得分提升9.0%，在SOTOPIA-Hard上提升4.1%，并略微优于直接观察意图的“理想”代理。这些初步结果表明，概率意图建模有助于提升LLM代理的社会智能水平。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。