DialRouter applies MCTS to generate training trajectories for a routing policy that optimizes cumulative rewards across multi-turn dialogues instead of myopic per-turn selection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue
DialRouter applies MCTS to generate training trajectories for a routing policy that optimizes cumulative rewards across multi-turn dialogues instead of myopic per-turn selection.