Software agents answer behavioral questions about code, such as whether a patch passes tests or which lines caused a failure. These tasks require repository-wide evidence, yet most scaffolds leave intermediate findings in free-form trajectories, making them hard to reuse and easy to disconnect from final answers. We pr...
Yi-Feng He, Yan-Jun Wang, Siwei Cui et al.· 0 citations
Reinforcement learning for code usually rewards passing tests, which a model can do while remaining wrong on the inputs the tests do not cover. A program verifier instead decides whether a program satisfies a formal specification for all inputs. Language models are almost always paired with verifiers at inference time...
George Ma, Yu-Hao Zhang, B. He et al.· 0 citations
As AI agents increasingly tackle complex repository-level coding tasks, distributing work across multiple agents is a natural way to scale beyond the capabilities of a single agent. To coordinate their interdependent work, these agents share findings and agree on interfaces between modules. However, exchanged informati...
Jia-Qi Xue, Yan-Jun Wang, Xiangci Li et al.· 0 citations
Autonomous coding agents solve repository issues by reading code, running commands, editing files, and submitting patches. Extra inference-time compute yields gains only when it produces a useful repair and supplies reliable evidence for choosing one. Three behaviors decide both, and we argue they are teachable rather...
Muhammad Ahmed Mohsin, Myeongsoo Kim, Kang-Rui Ruan et al.· 0 citations
This work presents Benchproofer, a pipeline that turns a coding task with a known correct patch into a formally verified one, which writes a specification for the new code, summarizes the existing functions that code calls with axioms, and admits an instance only after mechanical and adversarial gates agree.
George Ma, Benjamin Mikek, Hao-Yu Li et al.· 2 citations
Ensuring the correctness of LLM-generated code is a core challenge for modern software engineering. Benchmarks for agentic code generation check correctness with held-out test suites, which are inherently incomplete and increasingly susceptible to memorization. Formal verification avoids both problems, but existing wor...
George Ma, Benjamin Mikek, Hao-Yu Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
