arXiv AI
SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 11
P$^{3}$: Joint Program-and-Proof Planning for Verified Code Generation
arXiv:2608. 09277v1 Announce Type: new Abstract: Verified code generation asks a large language model (LLM) to generate both an executable program and a machine-checkable proof that the program meets a formal specification, promising software that is correct by construction.
Hugging Face Trending Papers
Jul 7
Harnessing Code Agents for Automatic Software Verification
Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive theorem provers such as Coq require enormous expert effort. Large language models (LLMs) promise to generate these proofs automatically, yet existing approaches wire a fixed, human-designed proof strategy into the system and constrain the model to follow it (retrieving premises and predicting tactics one step at a time, or splitting goals by divide-and-conquer), and still prove only a fraction of their target theorems.
Hugging Face Trending Papers
Aug 13
Vero: Can AI Agents Build Formally Verified Software Repositories?
AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked proof of its specification, offers a stronger path toward trustworthy AI-generated software.
arXiv AI
Aug 14
Vero: Can AI Agents Build Formally Verified Software Repositories?
arXiv:2608. 13522v1 Announce Type: cross Abstract: AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code.
arXiv AI
Jul 8
Harnessing Code Agents for Automatic Software Verification
arXiv:2607. 06341v1 Announce Type: cross Abstract: Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive theorem provers such as Coq require enormous expert effort.
arXiv AI
Jun 30
Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving
arXiv:2606. 29493v1 Announce Type: new Abstract: Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-checked proof.