© 2026 LinearBytes Inc.
Search posts, tags, users, and pages
Alex Towell
Building open source tools at the intersection of ML, statistics, and cryptography
Does tree search help LLM reasoning? The literature can't decide. ReST-MCTS* says yes. AB-MCTS got a NeurIPS spotlight. "Limits of PRM-Guided Tree Search" says no: MCTS with a process reward model used 11x more tokens than best-of-N for zero accuracy...
No responses yet.