works on

From the 2 of 47 linked papers with an AI index.

activity
20242026
most citedFrom Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

4 citations · 11 across the 37 of their papers we have counts for

collaborators
Showing cs.SEShow all

17 papers · 1 filter

cs.SE2026

Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?

Zhi Chen, Zhensu Sun, Yuling Shi +2

The paper audits three repository-level performance‑optimization benchmarks (GSO, SWE‑Perf, SWE‑efficiency) to assess how reliably they measure coding agents, revealing issues with…

cs.SE2026

Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution

Haotian Lin, Silin Chen, Xiaodong Gu +8

The paper introduces ACQUIRE, a QA-driven framework that lets a language model ask targeted questions about a code repository to acquire explicit knowledge before generating patche…

cs.SE2026

FastContext: Training Efficient Repository Explorer for Coding Agents

Shaoqiu Zhang, Maoquan Wang, Yuling Shi +12

Large Language Model (LLM) coding agents have achieved strong results on software engineering tasks, yet repository exploration remains a major bottleneck: locating relevant code c…

cs.SE2026

Dockerless: Environment-Free Program Verifier for Coding Agents

Wenhao Zeng, Yuling Shi, Xiaodong Gu +10

Program verifiers play a central role in training coding agents, including selecting trajectories for supervised fine-tuning (SFT) and providing rewards for reinforcement learning…

cs.SE2026

LLM Agents Can See Code Repositories

Dongjian Ma, Silin Chen, Yufei Yang +3

Coding agents powered by large language models have demonstrated strong performance on software engineering tasks. Yet most agents consume repositories almost entirely as text, whi…

cs.SE2026

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Shaoqiu Zhang, Yuhang Wang, Jialiang Liang +8

Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary predi…