AI & ML
Towards Agentic Proof Harness Engineering
arXiv cs.SE0 views
arXiv:2610.23241v1 Announce Type: new Abstract: Formal verification of real-world projects requires substantial manual effort, from specifying correctness properties to constructing the infrastructure needed to check them. We envision verification agents that assist developers throughout this process. Among the many tasks involved, one stands out as both foundational and amenable to automation: proof-harness engineering. A proof harness defines an isolated verification environment for a program unit, such as a function or module, by providing symbolic inputs, initialization code, and models of its dependencies. Today, proof-harness engineering remains largely a manual task performed by verification engineers. To explore the potential of coding agents for this task, we propose an agentic proof-harness engineer that automatically constructs verifier-ready harnesses from a software project and a designated verification target. We combine the agent with formal soundness and precision guards to validate generated abstractions and guide their refinement. We evaluate the feasibility of our approach in an exploratory case study on curl and libuv, using three historical assertion violations already embedded in the source code as verification properties. Our results show that the agent successfully constructs proof harnesses that enable CBMC to detect all three violations. We further demonstrate the potential for reusing these harnesses with other verification tools.
Source:https://arxiv.org/abs/2610.23241PreviousEfficient Program Reduction for Library Fuzzing HarnessesNextMLOps-Bench: Benchmarking AI Agents on Production ML Engineering in Real Repositories
Related posts
The Autonomous Edge — Issue #13: Cheaper Agents, Harder Governance (Week of November 2, 2026)
0dev.to AI

Plano Físico vs Plano Funcional en AWS Networking: cómo los arquitectos senior resuelven lo que otros no ven
0dev.to AWS
We built Origami Tutor: free paper-craft lessons you can turn and replay in 3D
0dev.to WebDev
From two authorized photos to a short AI rap video (consent-first workflow)
0dev.to WebDev
Check a File Hash in the Browser, Without Uploading the File
0dev.to WebDev
Your AI keys were leaked at a platform. A local guard you can paste catches the abuse before the invoice.
0dev.to Security