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.
Deepseek-prover-v1
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
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.
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.
Lack of exploration from conditioning on prior answers is the primary reason parallel sampling outperforms sequential sampling in large reasoning models.
citing papers explorer
-
Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics
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.
-
Automatic Textbook Formalization
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.
-
Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving
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: Scaling Causal Reasoning with Increasingly Complex Causal Simulators
CauSim turns scarce causal reasoning labels into scalable supervised data by having LLMs incrementally construct complex executable structural causal models.
-
Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models
Lack of exploration from conditioning on prior answers is the primary reason parallel sampling outperforms sequential sampling in large reasoning models.