paper-with-me

홈 › Papers

Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics

2026-01-20 · Junqi Liu, Zihao Zhou, Zekai Zhu, Marco Dos Santos, Weikun He, Jiawei Liu, Ran Wang, Yunzhou Xie, Junqiao Zhao, Qiufeng Wang, Lihong Zhi, Jia Li, Wenda Li arxiv

Agentic systems have recently become the dominant paradigm for formal theorem proving, achieving strong performance by coordinating multiple models and tools. However, existing approaches often rely on task-specific pipelines and trained formal provers, limiting their flexibility and reproducibility. In this paper, we propose the paradigm that directly uses a general coding agent as a formal math reasoner. This paradigm is motivated by (1) A general coding agent provides a natural interface for diverse reasoning tasks beyond proving, (2) Performance can be improved by simply replacing the underlying base model, without training, and (3) MCP enables flexible extension and autonomous calling of specialized tools, avoiding complex design. Based on this paradigm, we introduce Numina-Lean-Agent, which combines Claude Code with Numina-Lean-MCP to enable autonomous interaction with Lean, retrieval of relevant theorems, informal proving and auxiliary reasoning tools. Using Claude Opus 4.5 as the base model, Numina-Lean-Agent solves all problems in Putnam 2025 (12 / 12), matching the best closed-source system. Beyond benchmark evaluation, we further demonstrate its generality by interacting with mathematicians to successfully formalize the Brascamp-Lieb theorem. We release Numina-Lean-Agent and all solutions at https://github.com/project-numina/numina-lean-agent.

📄 PDF Abstract BibTeX arXiv:2601.14027

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OProver: A Unified Framework for Agentic Formal Theorem Proving

2026-05-17 · David Ma, Kaijing Ma, Shawn Guo, Yunfeng Shi 외 arxiv

Recent progress in formal theorem proving has benefited from large-scale proof generation and verifier-aware training, but agentic proving is rarely integrated into prover training, appearing only at inference time. We p…

Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel Prover

2026-04-09 · Jui-Hui Chung, Hongzhou Lin, Lai Jiang, Shange Tang 외 arxiv

Heavy supervised fine-tuning on a target domain can strongly suppress capabilities that were present in the base model. We study this phenomenon in formal mathematics using Goedel-Prover-V2, an open-source model heavily …

SorryDB: Can AI Provers Complete Real-World Lean Theorems?

2026-03-03 · Austin Letson, Leopoldo Sarra, Auguste Poiroux, Oliver Dressler 외 arxiv

We present SorryDB, a dynamically-updating benchmark of open Lean tasks drawn from 78 real world formalization projects on GitHub. Unlike existing static benchmarks, often composed of competition problems, hillclimbing t…

MerLean: An Agentic Framework for Autoformalization in Quantum Computation

2026-02-18 · Yuanjie Ren, Jinzheng Li, Yidi Qi arxiv

We introduce MerLean, a fully automated agentic framework for autoformalization in quantum computation. MerLean extracts mathematical statements from \LaTeX{} source files, formalizes them into verified Lean~4 code built…

OpenProver: Agentic and Interactive Theorem Proving with Lean 4

2026-07-10 · Matěj Kripner, Milan Straka arxiv

In this system paper, we present OpenProver, an open-source system for LLM-driven automated theorem proving (ATP) with integrated Lean 4 formal verification. OpenProver integrates a Planner-Worker-Verifier architecture i…

Automated Theorem ProvingCode Generation