mlsanityData to 14 Oct 2026

Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement

arXiv 2606.06468 ↗First posted 4 Jun 2026cs.AIcited by 9

On the map: LLM agents and tool use → Educational agents and math problem solving

Abstract (arXiv)

We introduce Goedel-Architect, an agentic framework for formal theorem proving in Lean 4 centered on blueprint generation and refinement. A blueprint is a dependency graph of definitions and lemmas that builds up to the main theorem. First, Goedel-Architect generates a blueprint of formally stated definitions and lemmas, along with declared dependencies. This blueprint is optionally guided by a natural language proof. Then, a tool-equipped Lean prover component closes each open lemma node in parallel using relevant dependencies. Failed lemmas in turn drive refinement of the global blueprint. This strategy contrasts with other mainstream approaches which use recursive lemma decomposition, and can inefficiently loop on dead-end strategies. Using the open-weight DeepSeek-V4-Flash (284B-A13B) as the backbone, Goedel-Architect attains 99.2% pass@1 on MiniF2F-test and 75.6% pass@1 on PutnamBench. With an optional natural-language proof seeding the initial blueprint on the harder problems, we additionally close the remaining two MiniF2F-test problems (reaching 100%), lift PutnamBench to 88.8% (597/672), and solve 4/6 on IMO 2025, 11/12 on Putnam 2025, and 3/6 on USAMO 2026. This represents state-of-the-art performance for an open-source pipeline at a price point up to 500x less than comparable open-source pipelines.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use. Builds on 20 of its 28 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

20 of 28 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026A Minimal Agent for Automated Theorem Proving27 Feb
  2. 2026Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics20 Jan

Other references · 18

  1. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  2. 2021MiniF2F: a cross-system benchmark for formal Olympiad-level mathematicscited by 391
  3. 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 291
  4. 2025DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decompositioncited by 287
  5. 2024DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Datacited by 234
  6. 2024DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Searchcited by 197
  7. 2025Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learningcited by 180
  8. 2024PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competitioncited by 165
  9. 2025Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correctioncited by 154
  10. 2025Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Provingcited by 133
  11. 2025Seed-Prover: Deep and Broad Reasoning for Automated Theorem Provingcited by 101
  12. 2024Lean-STaR: Learning to Interleave Thinking and Provingcited by 68
6 more
  1. 2025Hilbert: Recursively Building Formal Proofs with Informal Reasoningcited by 60
  2. 2024TheoremLlama: Transforming General-Purpose LLMs into Lean4 Expertscited by 59
  3. 2025Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experiencecited by 44
  4. 2024HunyuanProver: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Provingcited by 33
  5. 2026LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learningcited by 7
  6. 2026LeanArchitect: Automating Blueprint Generation for Humans and AIcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 9.

9 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2026OProver: A Unified Framework for Agentic Formal Theorem Proving
  2. 2026Optimizing the Cost-Quality Tradeoff of Agentic Theorem Provers in Lean
  3. 2026DreamProver: Evolving Transferable Lemma Libraries via a Wake-Sleep Theorem-Proving Agent
  4. 2026Agentic Proving for Program Verification
  5. 2026OpenProver: Agentic and Interactive Theorem Proving with Lean 4
  6. 2026MechMath: Sorrifier-Driven Formal Decomposition Workflow for Automated Theorem Proving
  7. 2026LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
  8. 2025Prover Agent: An Agent-Based Framework for Formal Mathematical Proofs