Static program analysis finds bugs before software ships, and modern checkers for C/C++ depend on whole-program infrastructure: pointer analysis, value-flow tracking, taint analysis, and IFDS-based data flow on top of LLVM. Today’s LLVM-IR frameworks fall short. SVF, Phasar, and Lotus expose their analyses through C++...
Yue-Kang Li, Wei Li, Wei Song et al.· Proceedings of the 41st IEEE...· 0 citations
Coding agents are extended with agent skills, directories whose SKILL.md tells the model when and how to perform a task. Because skills come from independent sources (teams, developers, plugins, copied collections), an installed skill can be co-installed with a similar skill doing the same job, and the model picks betw...
Chao-Liang Yan, Zi-Hao Xu, Yue-Kang Li et al.· 0 citations
JevAdvBench is introduced, to the authors' knowledge the first adversarial benchmark for RLCD models, with 812 typed questions over 66 scenarios, and a black-box attack suite of 9,744 single-edit variants that each edit one part of a request, with billed input tokens confirming that the edit reached the model.
Jian-Yi Hu, Hang Zhang, Yi Liu et al.· 12 citations· ⚡3
RLCDAlignBench is presented, which benchmarks Jev on ten alignment failures: sycophancy, jailbreaks, deception, prompt injection, hallucination, privacy violation, social bias, reward hacking, concealing uncertainty, and power seeking.
Ruo-Qi Guo, Yi Liu, Ge-Lei Deng et al.· 6 citations
Tencent WorkBuddy Bench is introduced, a multi-domain evaluation suite for coding agents, and its construction methodology, scoring protocol, and a cross-model leaderboard are documents, with a cross-model leaderboard across several model families.
The results show that reliable malicious-Skill detection requires both broader cross-source benchmark coverage and evaluation that jointly measures attack detection and benign over-flagging.
Yue Wang, Yi Liu, Ge-Lei Deng et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
