TheoremGraph builds a unified statement-level dependency graph across informal arXiv math and formal Lean code via parsing, embeddings, and LLM validation, releasing the data and APIs for search and retrieval.
hub Canonical reference
Seed-prover 1.5: Mastering undergraduate-level theorem proving via learning from experience
Canonical reference. 88% of citing Pith papers cite this work as background.
20
Pith papers citing it
Background
88% of classified citations
hub tools
citation-role summary
background 7
baseline 1
citation-polarity summary
years
2026 20representative citing papers
Goedel-Architect introduces blueprint generation and iterative refinement for Lean 4 theorem proving, reaching 99.2% on MiniF2F-test and 75.6% on PutnamBench with DeepSeek-V4-Flash.
An LLM-based agent with Lean verification autonomously solved multiple open Erdős problems and OEIS conjectures in the first large-scale test.
LeanSearch v2 recovers 46.1% of ground-truth premise groups for research-level Lean 4 theorems within 10 candidates and raises fixed-loop proof success to 20%.
Current AI agents fail to reliably invent transferable ML methods on a controlled 140-task benchmark, and more test-time compute or context does not remove the scientific-judgment bottleneck.
DataPRM is an environment-aware generative process reward model that improves LLM data analysis agents by 7-11% on benchmarks via active verification and reflection-aware ternary rewards.
Rethlas+Archon automatically construct and Lean-verify a counterexample showing weak quasi-completeness does not imply quasi-completeness for Noetherian local rings.
Lean Atlas visualizes Lean 4 dependency graphs and applies Lean Compass to reduce the nodes needing human semantic review by 27-99% across six evaluated projects.
EDV decouples execution, distillation by a third-party agent, and consensus verification to filter erroneous trajectories in LLM agent experience learning, outperforming baselines on tau2-bench, Mind2Web, and MMTB.
Synthetic data improves models only in information-open generation-training loops with external signals, and coarser signals like binary correctness enable better generalization by converging to the most information-efficient component.
A minimal agentic system achieves competitive performance in automated theorem proving with a simpler design and lower cost than state-of-the-art methods.
An agentic theorem prover in Lean uses a control plane to route actions based on cost and success estimates, achieving 28.9% lower average cost than a fixed-step baseline on a PutnamBench subset while preserving performance.
STAR-PólyaMath introduces a multi-agent framework with meta-strategic supervision and state-machine orchestration that reports state-of-the-art and perfect scores on eight top math competition benchmarks.
The paper introduces the 'topological dual of a dataset' — translating observable-logic sequents into covering-sieve statements on Grothendieck sites — as a new input representation for neuro-symbolic AI systems like AlphaGeometry.
AI for math combines task-specific architectures and general foundation models to support research and advance AI reasoning capabilities.
Advanced language representations shape LLMs' schemas to improve knowledge activation and problem-solving.
Seed2.0 model series reports gains in reasoning, visual understanding, search, and reliability on intricate long-horizon tasks via an internal evaluation system.
citing papers explorer
-
TheoremGraph: Bridging Formal and Informal Mathematics
TheoremGraph builds a unified statement-level dependency graph across informal arXiv math and formal Lean code via parsing, embeddings, and LLM validation, releasing the data and APIs for search and retrieval.
-
Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement
Goedel-Architect introduces blueprint generation and iterative refinement for Lean 4 theorem proving, reaching 99.2% on MiniF2F-test and 75.6% on PutnamBench with DeepSeek-V4-Flash.
-
Advancing Mathematics Research with AI-Driven Formal Proof Search
An LLM-based agent with Lean verification autonomously solved multiple open Erdős problems and OEIS conjectures in the first large-scale test.
-
LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
LeanSearch v2 recovers 46.1% of ground-truth premise groups for research-level Lean 4 theorems within 10 candidates and raises fixed-loop proof success to 20%.
-
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Current AI agents fail to reliably invent transferable ML methods on a controlled 140-task benchmark, and more test-time compute or context does not remove the scientific-judgment bottleneck.
-
Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis
DataPRM is an environment-aware generative process reward model that improves LLM data analysis agents by 7-11% on benchmarks via active verification and reflection-aware ternary rewards.
-
Automated Conjecture Resolution with Formal Verification
Rethlas+Archon automatically construct and Lean-verify a counterexample showing weak quasi-completeness does not imply quasi-completeness for Noetherian local rings.
-
Lean Atlas: An Integrated Proof Environment for Scalable Human-AI Collaborative Formalization
Lean Atlas visualizes Lean 4 dependency graphs and applies Lean Compass to reduce the nodes needing human semantic review by 27-99% across six evaluated projects.
-
Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning
EDV decouples execution, distillation by a third-party agent, and consensus verification to filter erroneous trajectories in LLM agent experience learning, outperforming baselines on tau2-bench, Mind2Web, and MMTB.
-
An Information-Theoretic Criterion for Efficient Data Synthesis
Synthetic data improves models only in information-open generation-training loops with external signals, and coarser signals like binary correctness enable better generalization by converging to the most information-efficient component.
-
A Minimal Agent for Automated Theorem Proving
A minimal agentic system achieves competitive performance in automated theorem proving with a simpler design and lower cost than state-of-the-art methods.
-
Optimizing the Cost-Quality Tradeoff of Agentic Theorem Provers in Lean
An agentic theorem prover in Lean uses a control plane to route actions based on cost and success estimates, achieving 28.9% lower average cost than a fixed-step baseline on a PutnamBench subset while preserving performance.
-
STAR-P\'olyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision
STAR-PólyaMath introduces a multi-agent framework with meta-strategic supervision and state-machine orchestration that reports state-of-the-art and perfect scores on eight top math competition benchmarks.
-
The Topological Dual of a Dataset: A Logic-to-Topology Encoding for AlphaGeometry-Style Data
The paper introduces the 'topological dual of a dataset' — translating observable-logic sequents into covering-sieve statements on Grothendieck sites — as a new input representation for neuro-symbolic AI systems like AlphaGeometry.
-
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.
-
Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding
Advanced language representations shape LLMs' schemas to improve knowledge activation and problem-solving.
-
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Seed2.0 model series reports gains in reasoning, visual understanding, search, and reliability on intricate long-horizon tasks via an internal evaluation system.
- Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics
- Scaling Self-Play with Self-Guidance
- Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs