CW
Chengpeng Wang
cs.SEcs.AIcs.PLcs.CRcs.LGcs.CL
On Valency
published · living versionsW_xxg2x9g5·v1 · currentpublished
God Does Not Play Dice: Enforcing Batch Invariance in Agentic Kernel Generation
with Youwei Bao, Simin Chen
1 version
Preprints & journals
20 papers in the corpus · 2023–2026To Cache or Not to Cache: Understanding and Mitigating Safety Incompatibility in Cross-Model KV Cache Reuse2610.15721v1 · Zhiwei Lin, Jiahao Liu, Yan Liu et al.2026 · 0 citationsarXiv
WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses2609.36635v1 · Haomin Qi, Xiangzhe Xu, Yiming Huang et al.2026 · 0 citationsarXiv
DatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis2609.37233v1 · Yuan Li, Hanyun Jiang, Guowei Tian et al.2026 · 0 citationsarXiv
SLBench: Evaluating How LLM Agents Follow Logical Relations in Skills2607.09016v1 · Xuan Chen, Chengpeng Wang, Lu Yan et al.2026 · 0 citationsarXiv
HintPilot: LLM-based Compiler Hint Synthesis for Code Optimization2604.15041v1 · Hanyun Jiang, Peisen Yao, Kaiyue Li et al.2026 · 2 citationsarXiv
DAInfer+: Neurosymbolic Inference of API Specifications from Documentation via Embedding Models2603.28060v1 · Maryam Masoudian, Anshunkang Zhou, Chengpeng Wang et al.2026 · 0 citationsarXiv
Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent2602.06325v1 · Zhou Xuan, Xiangzhe Xu, Mingwei Zheng et al.2026 · 0 citationsarXiv
Position: Intelligent Coding Systems Should Write Programs with Justifications2508.06017v1 · Xiangzhe Xu, Shiwei Feng, Zian Su et al.2025 · 0 citationsarXiv
ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants2508.03936v1 · Xiangzhe Xu, Guangyu Shen, Zian Su et al.2025 · 0 citationsarXiv
BugScope: Learn to Find Bugs Like Human2507.15671v2 · Jinyao Guo, Chengpeng Wang, Dominic Deluca et al.2025 · 1 citationarXiv
CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks2507.05269v3 · Danning Xie, Mingwei Zheng, Xuwei Liu et al.2025 · 3 citationsarXiv
RFCAudit: An LLM Agent for Functional Bug Detection in Network Protocols2506.00714v2 · Mingwei Zheng, Chengpeng Wang, Xuwei Liu et al.2025 · 2 citationsarXiv
Raw Pointer Rewriting with LLMs for Translating C to Safer Rust2505.04852v3 · Yifei Gao, Chengpeng Wang, Pengxiang Huang et al.2025 · 3 citationsarXiv
Validating Network Protocol Parsers with Traceable RFC Document Interpretation2504.18050v1 · Mingwei Zheng, Danning Xie, Qingkai Shi et al.2025 · 13 citationsarXiv
RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing2501.18160v3 · Jinyao Guo, Chengpeng Wang, Xiangzhe Xu et al.2025 · 4 citationsarXiv
NESA: Relational Neuro-Symbolic Static Program Analysis2412.14399v2 · Chengpeng Wang, Yifei Gao, Wuqi Zhang et al.2024 · 2 citationsarXiv
REPOFUSE: Repository-Level Code Completion with Fused Dual Context2402.14323v2 · Ming Liang, Xiaoheng Xie, Gehao Zhang et al.2024 · 6 citationsarXiv
LLMDFA: Analyzing Dataflow in Code with Large Language Models2402.10754v2 · Chengpeng Wang, Wuqi Zhang, Zian Su et al.2024 · 12 citationsarXiv
Synthesizing Conjunctive Queries for Code Search2305.04316v2 · Chengpeng Wang, Peisen Yao, Wensheng Tang et al.2023 · 3 citationsarXiv
Verifying Data Constraint Equivalence in FinTech Systems2301.11011v1 · Chengpeng Wang, Gang Fan, Peisen Yao et al.2023 · 7 citationsarXiv
Career total: 49 works. 20 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.