While coverage-guided kernel fuzzers have been proposed to uncover Linux kernel vulnerabilities, their code coverage and bug-finding capability are limited due to the lack of seed diversity, which is caused by the compounding effect of initial seed generation, seed scheduling, and seed mutation. To address this limitat...
Kun Hu, Jia-Ji Qin, Chao-Feng Sha et al.· Proceedings of the ACM on So...· 0 citations
This work proposes a novel model dependency recovering framework Tensorlock, which substantially outperforms state-of-the-art approaches in clustering and dependency identification, and applies it to 289 supposedly isolated models and recover 189 previously missing model dependencies.
Su-Sheng Wu, Zi-Qian Chen, Cheng-Yuan Li et al.· Proceedings of the ACM on So...· 0 citations
With the rapid development of autonomous driving systems (ADSs), it has become critical to ensure their operational safety, leading to the widespread adoption of simulation testing. While existing scenario-based simulation testing approaches have demonstrated effectiveness in detecting safety violations, they often fal...
You Lu, Ding-Ji Wang, Kun Zhang et al.· Proceedings of the ACM on So...· 0 citations
SkillSentry is proposed, a skill-oriented runtime assurance framework built upon a new domain-specific language (DSL) for representing runtime guidance for skill execution that improves the task success rate of LLM agents by 24.1% across skills, on average, while exhibiting lower variability across repeated runs.
You Lu, Xinyu Huang, Bi-Huan Chen et al.· 1 citation
Results show that DocsChisel improves the task success rate of LLM agents by 95.89% over the original tool documentation and by 75.15%, on average, over existing baselines, while incurring limited optimization time and token overhead.
You Lu, Kun Zhang, Bi-Huan Chen et al.· 0 citations
Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into explicit execution structures. However, constructing high-quality agentic workflows remains largely manual and requires substantial domain e...
Hao Shuo, Lu You, Bi-Huan Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.