作者位次 #3/3ACL 2026Poster· Natural Language Processing
Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate
John Seon Keun Yi · Aaron Mueller · Dokyun Lee
摘要
Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a framework that distills multi-agent debate into a single LLM th...