1.3k citations · 2.1k across the 28 of their papers we have counts for
10 papers · 1 filter
The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior
Xiangzhe Xu, Hamidreza Saghir, Qianhui Wu +5
As large language models continue to improve, agentic systems are becoming increasingly important, and tools are a key design dimension because they determine how agents access inf…
SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair
Yifan Zhang, Jieyu Li, Kexin Pei +2
Large Language Models (LLMs) can generate plausible code patches, but plausibility is not enough for automated repair: a patch must compile, pass tests, and remove the target vulne…
The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs
Haonan Li, Hang Zhang, Kexin Pei +1
Static analysis plays a crucial role in software vulnerability detection, yet faces a persistent precision-scalability tradeoff. In large codebases like the Linux kernel, tradition…
Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency
Jun Yang, Cheng-Chi Wang, Bogdan Alexandru Stoica +1
Large Language Models (LLMs) have been increasingly used to optimize code efficiency. Evaluating their effectiveness and further suggesting optimization opportunities often rely on…
EditLord: Learning Code Transformation Rules for Code Editing
Weichen Li, Albert Jan, Baishakhi Ray +3
Code editing is a foundational task in software development, where its effectiveness depends on whether it introduces desired code property changes without changing the original co…
SmartInv: Multimodal Learning for Smart Contract Invariant Inference
Sally Junsong Wang, Kexin Pei, Junfeng Yang
Smart contracts are software programs that enable diverse business activities on the blockchain. Recent research has identified new classes of "machine un-auditable" bugs that aris…
Detecting Buggy Contracts via Smart Testing
Sally Junsong Wang, Jianan Yao, Kexin Pei +2
Smart contracts are susceptible to critical vulnerabilities. Hybrid dynamic analyses, such as concolic execution assisted fuzzing and foundation model assisted fuzzing, have emerge…
TRACED: Execution-aware Pre-training for Source Code
Yangruibo Ding, Ben Steenhoek, Kexin Pei +3
Most existing pre-trained language models for source code focus on learning the static code text, typically augmented with static code structures (abstract syntax tree, dependency…
TraceFixer: Execution Trace-Driven Program Repair
Islem Bouzenia, Yangruibo Ding, Kexin Pei +2
When debugging unintended program behavior, developers can often identify the point in the execution where the actual behavior diverges from the desired behavior. For example, a va…
DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars
Yuchi Tian, Kexin Pei, Suman Jana +1
Recent advances in Deep Neural Networks (DNNs) have led to the development of DNN-driven autonomous cars that, using sensors like camera, LiDAR, etc., can drive without any human i…