Paper PDFs
Local copies synced from /mypaper.
Accepted
To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair
ISSTA 2026
Program RepairCode Agents
How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring
ISSTA 2026
Static AnalysisCode Agents
Phantom Rendering Detection: Identifying and Analyzing Unnecessary UI Computations
FSE 2026
Performance
MazeBreaker: Multi-Agent Reinforcement Learning for Dynamic Jailbreaking of LLM Security Defenses
ICSE 2026
LLM Security
HapRepair: Learn to Repair OpenHarmony Apps
FSE Industry 2025
Program RepairStatic Analysis
Effective Fine-tuning for Low-resource Languages: A Case Study of Cangjie
EMSE 2026
Misc
Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning
TOSEM 2024
Survey
Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs
TOSEM 2026
Static Analysis
Manuscripts (Short Intro)
RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue
Studies whether deployed LLM agents can rescue old repositories broken by runtime and dependency drift, with source-only auditing, runtime blocking, and realistic-use validation.
AtomicCommitBench: Can Coding Agents Reconstruct Commit Histories from Squashed Patches?
Benchmarks whether coding agents can reconstruct replayable, reviewable commit histories from squashed patches, measuring replay validity, human-aligned grouping, and selective-revert failure containment.
Executing as You Generate: Hiding Execution Latency in LLM Code Generation
Proposes EAGER, a parallel execution paradigm for LLM code generation that overlaps code generation and execution, reducing end-to-end latency by up to 55%.