PAC-MCTS supplies bias-aware confidence bounds for pruning in LLM-guided MCTS, with O((Δ-4L)^{-2}) upper and Ω((Δ-2L)^{-2}) lower sample-complexity guarantees and up to 78% fewer API calls on Blocksworld and ALFWorld.
Continuous Judgment Tasks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
PAC-MCTS: Bias-Aware Pruning for Robust LLM-Guided Search and Planning
PAC-MCTS supplies bias-aware confidence bounds for pruning in LLM-guided MCTS, with O((Δ-4L)^{-2}) upper and Ω((Δ-2L)^{-2}) lower sample-complexity guarantees and up to 78% fewer API calls on Blocksworld and ALFWorld.
- AMEL: Accumulated Message Effects on LLM Judgments