An RL-guided MCTS proof search for Tamarin finds more and shorter proofs than standard search across 16 protocol models.
hub
Deepseek-prover-v1
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
CAM-Bench is a new Lean 4 theorem-proving benchmark of 1,000 problems in computational and applied mathematics, built from textbook exercises using a dependency-recovery pipeline to reconstruct local context.
Re²Math is a new benchmark that evaluates AI models on retrieving and verifying the applicability of theorems from math literature to advance steps in partial proofs, accepting any sufficient theorem while controlling for leakage.
Multi-agent AI system formalizes entire 500-page graduate algebraic combinatorics textbook into Lean, creating 130K lines of code in one week at human-expert cost.
A Lean library called Palamedes uses synthesis rules from generator semantics and catamorphism-anamorphism rewriting to automatically produce correct constrained random generators.
LCPO trains L1 reasoning models to adhere to prompt-specified CoT lengths, supporting accuracy-compute trade-offs and yielding short reasoning models that outperform larger baselines at matched lengths.
Lean Refactor uses retrieval from a curated multi-objective strategy database to guide frozen LLMs in refactoring Lean proofs, reporting over 70% token compression on benchmarks and improved version transfer.
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.
CauSim turns scarce causal reasoning labels into scalable supervised data by having LLMs incrementally construct complex executable structural causal models.
A minimal agentic system achieves competitive performance in automated theorem proving with a simpler design and lower cost than state-of-the-art methods.
Ax-Prover is a tool-using multi-agent LLM system that matches state-of-the-art provers on public math benchmarks and outperforms them on new abstract-algebra and quantum-theory benchmarks while also assisting an expert with a cryptography proof.
RLVR training raises verified Dafny pass rates from 9.7% to 31.1% on a filtered benchmark while a Lean proof scaffold lifts success from 46.2% to 69.2% on a pilot set and solves 7 of 42 prior unsolved tasks.
Lack of exploration from conditioning on prior answers is the primary reason parallel sampling outperforms sequential sampling in large reasoning models.
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.
citing papers explorer
-
The Search for Constrained Random Generators
A Lean library called Palamedes uses synthesis rules from generator semantics and catamorphism-anamorphism rewriting to automatically produce correct constrained random generators.