AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimensional Quantum Mechanics
为解决物理领域理论论证的严谨性问题，通过构建AxQM基准测试集，使用Lean证明助手自动生成教科书规模的量子力学形式化证明。
0 citationsRead paper
Selected work
Representative Papers
AxDafny: Agentic Verified Code Generation in Dafny
This work addresses the challenge of simultaneously generating executable code and formal verification artifacts—such as invariants, assertions, and termination proofs—in Dafny. It proposes a verifier-guided repair framework that, for the first time, deeply integrates agent-driven code generation with Dafny’s formal verification capabilities. By establishing an iterative feedback loop between a large language model and the Dafny verifier, the approach co-generates program implementations and their accompanying verification constructs. The study also introduces LCB-Pro-Dafny, the first Dafny verification benchmark tailored to competition-level problems. Experimental results demonstrate that the method achieves a 92.7% verification success rate on DafnyBench, surpassing the previous state-of-the-art baseline by 6.5 percentage points, while further revealing an orthogonality between verification success and runtime test performance.
0 citationsRead paper
A Minimal Agent for Automated Theorem Proving
This work addresses the lack of concise and reproducible baseline systems in AI-driven automated theorem proving, which hinders fair architectural comparisons. To this end, we propose a minimalist yet competitive proof agent that integrates three core mechanisms: iterative proof refinement, theorem library retrieval, and context management. The system enables systematic evaluation of diverse large language models and design choices, achieving performance on par with state-of-the-art methods across multiple heterogeneous benchmarks. Our experiments demonstrate that iterative proof generation significantly outperforms single-pass generation, offering superior sample efficiency and reduced inference cost. The codebase is publicly released to provide the community with a standardized reference implementation.
0 citationsRead paper
Recent publications
Latest Papers
AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimensional Quantum Mechanics
为解决物理领域理论论证的严谨性问题，通过构建AxQM基准测试集，使用Lean证明助手自动生成教科书规模的量子力学形式化证明。
0 citationsRead paper
AxDafny: Agentic Verified Code Generation in Dafny
This work addresses the challenge of simultaneously generating executable code and formal verification artifacts—such as invariants, assertions, and termination proofs—in Dafny. It proposes a verifier-guided repair framework that, for the first time, deeply integrates agent-driven code generation with Dafny’s formal verification capabilities. By establishing an iterative feedback loop between a large language model and the Dafny verifier, the approach co-generates program implementations and their accompanying verification constructs. The study also introduces LCB-Pro-Dafny, the first Dafny verification benchmark tailored to competition-level problems. Experimental results demonstrate that the method achieves a 92.7% verification success rate on DafnyBench, surpassing the previous state-of-the-art baseline by 6.5 percentage points, while further revealing an orthogonality between verification success and runtime test performance.
0 citationsRead paper
A Minimal Agent for Automated Theorem Proving
This work addresses the lack of concise and reproducible baseline systems in AI-driven automated theorem proving, which hinders fair architectural comparisons. To this end, we propose a minimalist yet competitive proof agent that integrates three core mechanisms: iterative proof refinement, theorem library retrieval, and context management. The system enables systematic evaluation of diverse large language models and design choices, achieving performance on par with state-of-the-art methods across multiple heterogeneous benchmarks. Our experiments demonstrate that iterative proof generation significantly outperforms single-pass generation, offering superior sample efficiency and reduced inference cost. The codebase is publicly released to provide the community with a standardized reference implementation.
0 citationsRead paper