2 citations · 3 across the 12 of their papers we have counts for
13 papers
Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents
Zhensheng Zou, Guoqing Wang, Dan Hao
Tool observations dominate the context of software-engineering agents, making long interaction histories costly to maintain. Existing context compression methods can discard inform…
DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation
Zhihao Gong, Junzhe Yu, Dong Huang +3
Current data science (DS) code generation benchmarks equate correctness with quality, overlooking execution time differences that span orders of magnitude between correct solutions…
CausalRepair: Bridging the Causality Gap in Large Language Model-Based Automated Program Repair via Dual-Slicing
Linhao Wu, Yizhou Chen, Zhen Yang +2
Automated Program Repair (APR) has recently benefited from Large Language Models (LLMs), yet their effectiveness heavily depends on repair context. Existing LLM-based APR methods s…
WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning
Tianlu Qiao, Mingxuan Zhu, Zeyu Sun +1
Compilers are fundamental software tools that translate high-level programs into machine code. Modern compilers expose hundreds of optimizations, each turned on or off through an o…
GapForge: Directed Compiler Fuzzing via Coverage-Gap Analysis
Mingxuan Zhu, Qingyuan Liang, Junjie Chen +2
Modern compiler codebases (e.g., GCC and LLVM) are large and complex, making comprehensive coverage across diverse code regions highly challenging. Most existing test generation te…
DebugRepair: Enhancing LLM-Based Automated Program Repair via Self-Directed Debugging
Linhao Wu, Yifei Pei, Zhen Yang +9
Automated Program Repair (APR) has benefited from the code understanding and generation capabilities of Large Language Models (LLMs). Existing feedback-based APR methods iterativel…
TestDecision: Sequential Test Suite Generation via Greedy Optimization and Reinforcement Learning
Guoqing Wang, Chengran Yang, Xiaoxuan Zhou +4
With the rapid evolution of LLMs, automated software testing is witnessing a paradigm shift. While proprietary models like GPT-4o demonstrate impressive capabilities, their high de…
TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation
Zhihao Gong, Zeyu Sun, Dong Huang +3
While Large Language Models (LLMs) have substantially improved the functional correctness of code translation, the critical dimension of \textit{execution efficiency} remains overl…
Search-Induced Issues in Web-Augmented LLM Code Generation: Detecting and Repairing Error-Inducing Pages
Guoqing Wang, Zeyu Sun, Xiaofei Xie +4
Web-augmented large language models (LLMs) offer promising capabilities for automatic code generation. However, integrating live web search exposes models to unreliable or maliciou…
TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation
Zhihao Gong, Zeyu Sun, Dong Huang +3
While Large Language Models (LLMs) have substantially improved the functional correctness of code translation, the critical dimension of execution efficiency remains overlooked. We…
Automatically Learning a Precise Measurement for Fault Diagnosis Capability of Test Cases
Yifan Zhao, Zeyu Sun, Guoqing Wang +5
Prevalent Fault Localization (FL) techniques rely on tests to localize buggy program elements. Tests could be treated as fuel to further boost FL by providing more debugging inform…
Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?
Guoqing Wang, Zeyu Sun, Zhihao Gong +5
Large Language Models (LLMs) have significantly advanced software engineering (SE) tasks, with prompt engineering techniques enhancing their performance in code-related areas. Howe…
Improving Smart Contract Security with Contrastive Learning-based Vulnerability Detection
Yizhou Chen, Zeyu Sun, Zhihao Gong +1
Currently, smart contract vulnerabilities (SCVs) have emerged as a major factor threatening the transaction security of blockchain. Existing state-of-the-art methods rely on deep l…