AI RESEARCH
From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue
arXiv CS.CL
•
ArXi:2604.12385v1 Announce Type: new Multi-turn dialogue is the predominant form of interaction with large language models (LLMs). While LLM routing is effective in single-turn settings, existing methods fail to maximize cumulative performance in multi-turn dialogue due to interaction dynamics and delayed rewards. To address this challenge, we move from myopic, single-turn selection to long-horizon sequential routing for multi-turn dialogue.