Year: 2025
Type: conference-paper
Abstract: Non-cooperative dialogues, such as negotiations and persuasion, present significant challenges for large language models (LLMs) due to the lack of inherent cooperation or shared goals.Current methods for optimizing dialogue strategies require substantial human effort for strategy optimization.To address these challenges, we propose ASTRO (Automated Strategy Optimization), a fully automated solution that leverages LLMs' self-envolving capabilities.ASTRO dynamically generates customized strategy sets based on task goals and optimizes strategy planner using a self-play reinforcement learning paradigm.Our experimental results demonstrate ASTRO's significant performance improvements over baseline models across various non-cooperative dialogue tasks, highlighting the potential for autonomously developing such agents without human intervention.Our code is available at https://github.com/SCUNLP/ASTRO....... How much is this computer?The listed price is $999.How about $800?It's a bit pricey compared to others....... How should I respond?Strategy Planner
Authors: Yikuan Hu, Chen Huang, Wenqiang Lei
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Awards: G1289754401, G5411532798, G6978877745
OpenAlex ID: W4412888910