AsyncMLD: Asynchronous Multi-LLM Framework for Dialogue Recommendation System
This work addresses efficiency issues in dialogue agents for users needing expert knowledge, but it appears incremental as it builds on existing LLM methods with threading optimizations.
The paper tackles the problem of slow response times and ineffective content in dialogue recommendation systems by proposing an asynchronous multi-LLM framework that performs database searches concurrently with robot speech, resulting in improved efficiency and effectiveness.
We have reached a practical and realistic phase in human-support dialogue agents by developing a large language model (LLM). However, when requiring expert knowledge or anticipating the utterance content using the massive size of the dialogue database, we still need help with the utterance content's effectiveness and the efficiency of its output speed, even if using LLM. Therefore, we propose a framework that uses LLM asynchronously in the part of the system that returns an appropriate response and in the part that understands the user's intention and searches the database. In particular, noting that it takes time for the robot to speak, threading related to database searches is performed while the robot is speaking.