DL
David Lo
cs.SEcs.CRcs.AIcs.LGcs.CLcs.PLcs.IRcs.SIcs.CYcs.HC
On Valency
published · living versionsW_hwsxy87x·v1 · currentpublished
ExploreRepair: Evidence-Specialized Agents for Vulnerability Repair under Information Constraints
with Duc Manh Tran, Ratnadira Widyasari, Ivana Clairine Irsan, Huihui Huang +3
1 version
W_7yh5gqdq·v1published
W_uxtscr5p·v1published
Preprints & journals
274 papers in the corpus · 2016–2026Towards Scalable and Cost-Efficient Vulnerability Detection: A Study on Automatic Query Generation2609.10412v1 · Ivana Clairine Irsan, Ratnadira Widyasari, Huihui Huang et al.2026 · 0 citationsarXiv
Talking to Itself While Coding: What Makes Comments Help Code Generation?2609.09242v1 · Dangfeng Pan, Zhensu Sun, Cenyuan Zhang et al.2026 · 0 citationsarXiv
Learning from the Test: Self-Referential Differential Testing for Deep RL Agents2608.22284v1 · Junda He, Jieke Shi, Zhou Yang et al.2026 · 0 citationsarXiv
CoSA: Context-Aware Severity Assessment via Context Analysis with Large Language Models2608.13928v1 · Jinfeng Jiang, Yikun Li, Chengran Yang et al.2026 · 0 citationsarXiv
Second Thought: Reasoning in Parallel as LLM Agents Act and Observe2608.13667v1 · Zhensu Sun, Chengran Yang, Yunbo Lyu et al.2026 · 0 citationsarXiv
Lossless Tensor Compression as Program Synthesis2608.02162v1 · Jieke Shi, Junda He, Wenjia Jiang et al.2026 · 0 citationsarXiv
Vul4Py: Benchmarking Automated Vulnerability Repair in Python with Paired Exploit and Functional Oracles2608.00692v1 · Tan Bui, Ting Zhang, Ferdian Thung et al.2026 · 0 citationsarXiv
Demystifying Solana Bots: From GitHub Blueprints to On-Chain Fingerprints2607.28424v2 · Xiaoye Zheng, Yujing Chen, Minghao Wu et al.2026 · 0 citationsarXiv
Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection2607.26656v1 · Yikun Li, Ting Zhang, Jiakun Liu et al.2026 · 0 citationsarXiv
"Go Home Copilot, You're Drunk": Understanding Developer Responses to Agent-Generated Code Review Comments2607.21997v2 · Shamse Tasnim Cynthia, Ratnadira Widyasari, Banani Roy et al.2026 · 0 citationsarXiv
PoCEvolve: Generating Proof-of-Concept Exploits from Security Patches with Vulnerability-Aware Prompt Evolution2607.22076v1 · Duc Manh Tran, Ratnadira Widyasari, Ivana Clairine Irsan et al.2026 · 0 citationsarXiv
Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation2607.17619v1 · Yuchen Chen, Wei Cheng, Yuan Xiao et al.2026 · 0 citationsarXiv
How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study2607.10856v2 · Yunbo Lyu, David Williams, Jieke Shi et al.2026 · 0 citationsarXiv
Agent System Operations: Categorization, Challenges, and Future Directions2606.01581v2 · Zexin Wang, Changhua Pei, Yuanhao Liu et al.2026 · 0 citationsarXiv
How Agentic AI Coding Assistants Become the Attacker's Shell2605.25871v1 · Yue Liu, Yanjie Zhao, Yunbo Lyu et al.2026 · 0 citationsarXiv
Finding Missing Input Validation in TEEs via LLM-Assisted Symbolic Execution2605.22058v1 · Chengyan Ma, Jieke Shi, Ruidong Han et al.2026 · 1 citationarXiv
Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching2605.22087v1 · Chengyan Ma, Jieke Shi, Ruidong Han et al.2026 · 0 citationsarXiv
TitanCA: Lessons from Orchestrating LLM Agents to Discover 100+ CVEs2604.17860v3 · Ting Zhang, Yikun Li, Chengran Yang et al.2026 · 0 citationsarXiv
AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits2604.02665v1 · Yunbo Lyu, Jieke Shi, Hong Jin Kang et al.2026 · 0 citationsarXiv
Compiling Code LLMs into Lightweight Executables2603.29813v3 · Jieke Shi, Junda He, Zhou Yang et al.2026 · 0 citationsarXiv
Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis2603.27224v6 · Huihui Huang, Jieke Shi, Bo Wang et al.2026 · 0 citationsarXiv
Revisiting Vulnerability Patch Identification on Data in the Wild2603.17266v1 · Ivana Clairine Irsan, Ratnadira Widyasari, Ting Zhang et al.2026 · 0 citationsarXiv
ESG Reporting Lifecycle Management with Large Language Models and AI Agents2603.10646v1 · Thong Hoang, Mykhailo Klymenko, Xiwei Xu et al.2026 · 4 citationsarXiv
Virtualization-based Penetration Testing Study for Detecting Accessibility Abuse Vulnerabilities in Banking Apps in East and Southeast Asia2601.21258v1 · Wei Minn, Phong Phan, Vikas K. Malviya et al.2026 · 0 citationsarXiv
Future of Software Engineering Research: The SIGSOFT Perspective2601.19731v1 · Massimiliano Di Penta, Kelly Blincoe, Marsha Chechik et al.2026 · 0 citations2026 IEEE/ACM 48th International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE), April 12-18, 2026, Rio de Janeiro, Brazil
PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing2601.06910v1 · Huihui Huang, Jieke Shi, Junkai Chen et al.2026 · 1 citationarXiv
LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis2601.05539v2 · Gou Tan, Zilong He, Min Li et al.2026 · 0 citationsarXiv
Agentic Software Issue Resolution with Large Language Models: A Survey2512.22256v2 · Zhonghao Jiang, David Lo, Zhongxin Liu2025 · 4 citationsarXiv
What You Trust Is Insecure: Demystifying How Developers (Mis)Use Trusted Execution Environments in Practice2512.17363v3 · Yuqing Niu, Jieke Shi, Ruidong Han et al.2025 · 1 citationarXiv
Why Is My Transaction Risky? Understanding Smart Contract Semantics and Interactions in the NFT Ecosystem2512.17500v1 · Yujing Chen, Xuanming Liu, Zhiyuan Wan et al.2025 · 0 citationsarXiv
UniCoR: Modality Collaboration for Robust Cross-Language Hybrid Code Retrieval2512.10452v2 · Yang Yang, Li Kuang, Jiakun Liu et al.2025 · 1 citationarXiv
Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand2512.08266v1 · Zhensu Sun, Chengran Yang, Xiaoning Du et al.2025 · 0 citationsarXiv
A Systematic Literature Review of Code Hallucinations in LLMs: Characterization, Mitigation Methods, Challenges, and Future Directions for Reliable AI2511.00776v1 · Cuiyun Gao, Guodong Fan, Chun Yong Chong et al.2025 · 2 citationsarXiv
Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead2512.00020v3 · Guang Yang, Wei Zheng, Xiang Chen et al.2025 · 2 citationsarXiv
LLM-as-a-Judge for Software Engineering: Literature Review, Vision, and the Road Ahead2510.24367v1 · Junda He, Jieke Shi, Terry Yue Zhuo et al.2025 · 12 citationsarXiv
Trace: Securing Smart Contract Repository Against Access Control Vulnerability2510.19254v1 · Chong Chen, Jiachi Chen, Lingfeng Bao et al.2025 · 1 citationarXiv
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution2510.08697v2 · Terry Yue Zhuo, Xiaolong Jin, Hange Liu et al.2025 · 0 citationsarXiv
Bamboo: LLM-Driven Discovery of API-Permission Mappings in the Android Framework2510.04078v1 · Han Hu, Wei Minn, Yonghui Liu et al.2025 · 1 citationarXiv
Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework2510.01002v2 · Chengran Yang, Ting Zhang, Jinfeng Jiang et al.2025 · 0 citationsarXiv
Extending Fill-In-the-Middle with Instructions for Steerable Code Completion2509.24637v3 · Zhensu Sun, Chengran Yang, Chao Peng et al.2025 · 0 citationsarXiv
SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios2509.22097v5 · Junkai Chen, Huihui Huang, Yunbo Lyu et al.2025 · 2 citationsarXiv
Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning2509.13755v1 · Zhaoyang Chu, Yao Wan, Zhikun Zhang et al.2025 · 0 citationsarXiv
PatchSeeker: Mapping NVD Records to their Vulnerability-fixing Commits with LLM Generated Commits and Embeddings2509.07540v1 · Huu Hung Nguyen, Anh Tuan Nguyen, Thanh Le-Cong et al.2025 · 0 citationsarXiv
Curiosity-Driven Testing for Sequential Decision-Making Process2509.02025v1 · Junda He, Zhou Yang, Jieke Shi et al.2025 · 10 citationsarXiv
The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget2508.13666v1 · Dangfeng Pan, Zhensu Sun, Cenyuan Zhang et al.2025 · 0 citationsarXiv
"My productivity is boosted, but ..." Demystifying Users' Perception on AI Coding Assistants2508.12285v1 · Yunbo Lyu, Zhou Yang, Jieke Shi et al.2025 · 8 citationsarXiv
LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration Recommendations2508.09791v1 · Junxiao Han, Yarong Wang, Xiaodong Gu et al.2025 · 1 citationarXiv
Multi-Modal Requirements Data-based Acceptance Criteria Generation using LLMs2508.06888v1 · Fanyu Wang, Chetan Arora, Yonghui Liu et al.2025 · 0 citationsarXiv
Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?2507.21817v4 · Yikun Li, Ngoc Tan Bui, Ting Zhang et al.2025 · 2 citationsarXiv
Enhancing Project-Specific Code Completion by Inferring Internal API Information2507.20888v1 · Le Deng, Xiaoxue Ren, Chao Ni et al.2025 · 6 citationsarXiv
Career total: at least 900 works. 274 are in this corpus.Showing the 50 most recent.
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.