3 citations · 7 across the 25 of their papers we have counts for
15 papers · 1 filter
"Your Robot Was Trained on a Lie": Collision Mesh Poisoning Attacks on Robotic Manipulation
Gengyang Xu, Dongwei Xiao, Yiteng Peng +6
Learning-enabled robotic manipulation increasingly relies on robot simulators for policy training and evaluation before real-world deployment. Inside a simulator, a 3D asset contai…
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Yuling Shi, Jinghan Xu, Kelin Fu +12
As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under se…
Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports
Jingyi Chen, Songqiang Chen, Hengcheng Zhu +3
LLM agents span command-line interfaces (e.g., Codex) and agent frameworks (e.g., LangChain), integrating backend LLMs with harness code that parses model outputs, controls agent l…
Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills
Jialun Cao, Xinru Yan, Songqiang Chen +3
Software engineering (abbrev. SE) has continuously evolved through increasingly powerful forms of reuse, from source code and libraries to components and services. Recent advances…
Programming-by-Example for Batch-Editing Collision Meshes in 3D Software
Gengyang Xu, Dongwei Xiao, Hengcheng Zhu +4
As 3D software proliferates, software artifacts now extend beyond code and 2D user interfaces to include 3D assets. Among these assets, collision meshes are critical as they define…
Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware
Zimo Ji, Congying Xu, Zongjie Li +4
LLM coding agents increasingly rely on third-party agent skills from public marketplaces, which execute with the agent's privileges and create a software supply-chain attack surfac…
Coding Agents Are Guessing: Measuring Action-Boundary Violations in Underspecified DevOps Instructions
Zimo Ji, Zekai Zhang, Congying Xu +4
LLM coding agents are increasingly deployed to act autonomously on real production infrastructure. They execute shell commands, modify repositories, and call operational APIs. Howe…
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
Yuanyi Wang, Yifan Yang, Su Lu +9
Continual post-training aims to extend large language models (LLMs) with new knowledge, skills, and behaviors, yet it remains unclear when sequential updates enable capability tran…
LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation
Dong Xu, Jialun Cao, Guozhao Mo +9
Formal specification is essential for rigorous program verification, yet writing correct specifications remains costly and difficult to automate. Although large language models (LL…
GW240925 and GW250207: Astrophysical Calibration of Gravitational-wave Detectors
The LIGO Scientific Collaboration, the Virgo Collaboration, the KAGRA Collaboration +1839
GW240925 and GW250207 are two loud gravitational-wave signals from binary black hole coalescences observed with network signal-to-noise ratios and , respectively…
MR-Coupler: Automated Metamorphic Test Generation via Functional Coupling Analysis
Congying Xu, Hengcheng Zhu, Songqiang Chen +3
Metamorphic testing (MT) is a widely recognized technique for alleviating the oracle problem in software testing. However, its adoption is hindered by the difficulty of constructin…
Demystifying the Silence of Correctness Bugs in PyTorch Compiler
Meiziniu Li, Dongze Li, Jianmeng Liu +1
Performance optimization of AI infrastructure is key to the fast adoption of large language models (LLMs). The PyTorch compiler (torch.compile), a core optimization tool for deep l…
Can Large Language Models Model Programs Formally?
Zhiyong Chen, Jialun Cao, Jiarong Wu +2
In the digital age, ensuring the correctness, safety, and reliability of software through formal verification is paramount, particularly as software increasingly underpins critical…
SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark
Boxi Yu, Yang Cao, Yuzhong Zhang +9
The SWE-Bench Verified leaderboard is approaching saturation, with the top system achieving 78.80%. However, we show that this performance is inflated. Our re-evaluation reveals th…
CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems
Zongyi Lyu, Zhenlan Ji, Songqiang Chen +4
Despite the remarkable success that Multi-Agent Code Generation Systems (MACGS) have achieved, the inherent complexity of multi-agent architectures produces substantial volumes of…