11 papers
CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration
Jiayao Gu, Kexin Chu, Peidong Liu +5
LLM-based agents excel at writing articles, coding and information retrieval. However, they fail to form strong collaborations within the scientific community due to the bidirectio…
CXLMemUring: A Hardware Software Co-design Paradigm for Asynchronous and Flexible Parallel CXL Memory Pool Access
Yiwei Yang, Yusheng Zheng, Kexin Chu +3
CXL-attached memory lets servers add more memory while keeping the standard load/store programming model. The main drawback is latency. CXL memory accesses are too slow for normal…
MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference
Kexin Chu, Yang Zhou, Wei Zhang
Temperature-zero BF16 LLM inference is often treated as reproducible, yet the same request can emit different tokens when decoded alone or inside a larger batch. Existing fixes use…
Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents
Kexin Chu, Dawei Xiang, Wei Zhang
Tool-augmented LLM agents increasingly access the same tool type through multiple functionally equivalent providers, such as web-search APIs, retrievers, or LLM backends exposed be…
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
Kexin Chu
Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents…
Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
Kexin Chu, Zecheng Lin, Dawei Xiang +7
Global KV-cache sharing is an effective optimization for accelerating large language model (LLM) inference, yet it introduces an API-visible timing side channel that lets adversari…