Agent-directed tree search improves LLM performance on Lean formal verification tasks, with context-based orchestration solving more intermediate specs at lower token cost than baseline agents.
CoRR , volume =
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
OProver-32B achieves top Pass@32 scores on MiniF2F, ProverBench, and PutnamBench by combining continued pretraining with iterative agentic proving, retrieval, SFT on repairs, and RL on unresolved cases using a 6.86M-proof dataset.
Segment-level supervision extracts coherent proof segments to train policy models that achieve 61-66% success on miniF2F, outperforming step-level and whole-proof methods while also improving existing provers.
OptProver transfers formal theorem proving from Olympiad math to optimization via continual training, achieving SOTA Pass@1 and Pass@32 on a new Lean 4 benchmark while retaining general performance.
AI for math combines task-specific architectures and general foundation models to support research and advance AI reasoning capabilities.
citing papers explorer
-
AI for Mathematics: Progress, Challenges, and Prospects
AI for math combines task-specific architectures and general foundation models to support research and advance AI reasoning capabilities.