collaborators

11 papers

cs.SE2026

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…

cs.SE2026

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…

cs.CR2026

Symbolon: Symbolic Execution by Learning Code Transformation

Jie Zhu, Penghui Li, Zhongxuan Li +4

Symbolic execution is a powerful program analysis technique with broad applications, such as vulnerability detection, security testing, and malware analysis. However, this techniqu…

cs.CR2026

SoK: AI-Augmented Binary Reversing

Yujeong Kwon, Yiyue Zhang, Shakhzod Yuldoshkhujaev +3

Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it remains inherently challenging due to…

cs.PL2026

ExVerus: Verus Proof Repair via Counterexample Reasoning

Jun Yang, Yuechun Sun, Yi Wu +5

Large Language Models (LLMs) have shown promising results in automating formal verification. However, existing approaches treat proof generation as a static, end-to-end prediction…

cs.AI2026

R-C2: Cycle-Consistent Reinforcement Learning Improves Multimodal Reasoning

Zirui Zhang, Haoyu Dong, Kexin Pei +1

Robust perception and reasoning require consistency across sensory modalities. Yet current multimodal models often violate this principle, yielding contradictory predictions for vi…