5 papers
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
Tingxu Han, Yi Zhang, Wei Song +4
Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real ut…
Compartmentalization-Aware Automated Program Repair
Jia Hu, Youcheng Sun, Pierre Olivier
Software compartmentalization breaks down an application into compartments isolated from each other: an attacker taking over a compartment will be confined to it, limiting the dama…
ClawMobile: Rethinking Smartphone-Native Agentic Systems
Hongchao Du, Shangyu Wu, Qiao Li +4
Smartphones represent a uniquely challenging environment for agentic systems. Unlike cloud or desktop settings, mobile devices combine constrained execution contexts, fragmented co…
Exposing Hidden Interfaces: LLM-Guided Type Inference for Reverse Engineering macOS Private Frameworks
Arina Kharlamova, Youcheng Sun, Ting Yu
Private macOS frameworks underpin critical services and daemons but remain undocumented and distributed only as stripped binaries, complicating security analysis. We present MOTIF,…
LLM-Driven Kernel Evolution: Automating Driver Updates in Linux
Arina Kharlamova, Jiawen Liu, Tianyi Zhang +4
Linux kernel evolution breaks drivers through API/ABI changes, semantic shifts, and security-hardening updates. We introduce DRIVEBENCH, an executable corpus of kernel…