Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Feifan, Fang, Yuyang, Li, Defang, Xie, Yantong, Li, Weikang, Li, Yang, Xia, Deguo, Huang, Jizhou
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917029492031488
author Xia, Feifan
Fang, Yuyang
Li, Defang
Xie, Yantong
Li, Weikang
Li, Yang
Xia, Deguo
Huang, Jizhou
author_facet Xia, Feifan
Fang, Yuyang
Li, Defang
Xie, Yantong
Li, Weikang
Li, Yang
Xia, Deguo
Huang, Jizhou
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18476
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents
Xia, Feifan
Fang, Yuyang
Li, Defang
Xie, Yantong
Li, Weikang
Li, Yang
Xia, Deguo
Huang, Jizhou
Artificial Intelligence
Computation and Language
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.
title Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2510.18476