11 citations · 15 across the 8 of their papers we have counts for
6 papers · 1 filter
Agentic Interpretation: Harness-Governed Evidence Construction for Software Agents
Yifeng He, Yanjun Wang, Siwei Cui +2
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…
Verifier-Grounded Agentic RL for Provably Correct Code
George Ma, Yuhao Zhang, Bing He +5
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 w…
AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation
Jiaqi Xue, Yanjun Wang, Xiangci Li +5
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…
Teaching Agents to Code Reliably
Muhammad Ahmed Mohsin, Myeongsoo Kim, Kangrui Ruan +3
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 pr…
SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?
George Ma, Benjamin Mikek, Haoyu Li +9
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 suit…
CODESTRUCT: Code Agents over Structured Action Spaces
Myeongsoo Kim, Joe Hsu, Dingmin Wang +3
LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. W…