4 papers
TenonAgent: Virtualizing Execution Residency for Memory-Oversubscribed LLM Agents
Yifan Zhang, Xinkui Zhao, Ruixin Huang +8
LLM agents execute as long-lived, multi-stage workflows with substantial resource-demand variation across phases. Provisioning each agent or sandbox for its lifetime peak leads to…
FAVA: Formal Authorization for Verified Agents with Evidence-Backed Permission Graphs
Yifan Zhang, Xinkui Zhao, Sai Liu +3
Large language model (LLM) agents autonomously interleave semantic reasoning with complex system operations. In these dynamic environments, static tool-level permissions are fundam…
GRAB-ANNS: High-Throughput Indexing and Hybrid Search via GPU-Native Bucketing
Xinkui Zhao, Hengxuan Lou, Yifan Zhang +3
Hybrid search, which jointly optimizes vector similarity and structured predicate filtering, has become a fundamental building block for modern AI-driven systems. While recent pred…
MUSE: A Heterogeneity-Aware Multimedia Search Engine for Mobile SoCs
Xinkui Zhao, Qingyu Ma, Yifan Zhang +6
On-device multimedia retrieval is vital for smartphones, enabling applications like cross-modal semantic search and multimodal personal AI agents. However, realizing efficient retr…