5 papers
ActPlane: Programmable OS-Level Policy Enforcement for Agent Harnesses
Yusheng Zheng, Tianyuan Wu, Quanzhi Fu +6
AI agents increasingly run in production through harnesses, the software around the LLM, including an engine that enforces safety and effectiveness policies, e.g., 'run tests befor…
DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents
Jiamian Wang, Ruiyi Zhang, Tong Yu +5
Recent methods train search agents via reinforcement learning from (question, answer, evidence) tuples without requiring expert trajectories. The tuples serve as the training envir…
gpu_ext: Extensible OS Policies for GPUs via eBPF
Yusheng Zheng, Tong Yu, Yiwei Yang +8
Performance in modern GPU-centric systems increasingly depends on resource management policies, including memory placement, scheduling, and observability. However, uniform policies…
AgentSight: System-Level Observability for AI Agents Using eBPF
Yusheng Zheng, Yanpeng Hu, Tong Yu +1
Modern software infrastructure increasingly relies on LLM agents for development and maintenance, such as Claude Code and Gemini-cli. However, these AI agents differ fundamentally…
HetGPU: The pursuit of making binary compatibility towards GPUs
Yiwei Yang, Yusheng Zheng, Tong Yu +1
Heterogeneous GPU infrastructures present a binary compatibility challenge: code compiled for one vendor's GPU will not run on another due to divergent instruction sets, execution…