Method Drift›LLM reasoning / chain-of-thought
Superseded baseline#445 of 772 most-superseded
MCTS-based scoring
LLM reasoning / chain-of-thought
superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 0 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites MCTS-based scoring as a baseline.
“While we also use MCTS to construct data, we depart from relying solely on MC-score-based metrics as in visualprm.”
— Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.
- Verifiable Process Reward Models (VPRMs)Beyond Outcome Verification: Verifiable Process Reward Models for Structured ReasoningJan 23, 2026
- perception-focused supervisionTraining Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons LearnedSep 27, 2025