作者位次 #3/5ACL 2026Poster· Natural Language Processing
P rivacy- R 1: Privacy-Aware Multi- LLM Agent Collaboration via Reinforcement Learning
Zheng Hui · Yijiang River Dong · Sanhanat Sivapiromrat · Ehsan Shareghi · Nigel Collier
摘要
When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk data exposure, or relying on smaller, local models guara...