用博弈论提升多智能体对话效率，让语言更精准传达意图。
LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation
- 将对话建模为意图与策略的信号博弈，无需训练实时调整决策。
- 在法庭模拟和辩论中，人类专家评估显示沟通效率显著提升。
- 基于语言学推理，通用性强，适合复杂对话场景研究者。
大语言模型（LLMs）推动了多智能体系统（MASs）的发展，使智能体通过自然语言交互完成复杂任务或模拟多方对话。现有工作主要聚焦于架构设计，如角色分配和流程编排。本文则关注交互过程本身，旨在通过提升语言表达意图的有效性来增强智能体的沟通效率。为此，提出LinguaGame：一种基于语言学的博弈论多智能体对话生成范式。该方法将对话建模为通信意图与策略之间的信号博弈，采用无需训练的均衡近似算法实现推理时决策调整。与以往依赖任务特异性目标的博弈框架不同，本框架基于语言学启发的推理，任务耦合最小。具体而言，它将对话视为有目的、有策略的交流，要求智能体推断他人目标（意图）及实现方式（策略）。在模拟法庭程序和辩论场景中评估，人类专家评估显示沟通效率显著提升。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have enabled Multi-Agent Systems (MASs) where agents interact through natural language to solve complex tasks or simulate multi-party dialogues. Recent work on LLM-based MASs has mainly focused on architecture design, such as role assignment and workflow orchestration. In contrast, this paper targets the interaction process itself, aiming to improve agents' communication efficiency by helping them convey their intended meaning more effectively through language. To this end, we propose LinguaGame, a linguistically-grounded game-theoretic paradigm for multi-agent dialogue generation. Our approach models dialogue as a signalling game over communicative intents and strategies, solved with a training-free equilibrium approximation algorithm for inference-time decision adjustment. Unlike prior game-theoretic MASs, whose game designs are often tightly coupled with task-specific objectives, our framework relies on linguistically informed reasoning with minimal task-specific coupling. Specifically, it treats dialogue as intentional and strategic communication, requiring agents to infer what others aim to achieve (intents) and how they pursue those goals (strategies). We evaluate our framework in simulated courtroom proceedings and debates, with human expert assessments showing significant gains in communication efficiency.
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。