Xunzhuo Liu, Bowei He, Xue Liu, Andy Luo, Haichen Zhang, Huamin Chen

Articles by Xunzhuo Liu, Bowei He, Xue Liu, Andy Luo, Haichen Zhang, Huamin Chen

Academic · 1 min

Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents

arXiv:2603.23013v1 Announce Type: new Abstract: Production AI agents frequently receive user-specific queries that are highly repetitive, with up to 47\% being semantically similar to prior …

7 views Mar 25

Academic · 1 min

98$\times$ Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for …

arXiv:2603.12646v1 Announce Type: new Abstract: System-level routers that intercept LLM requests for safety classification, domain routing, and PII detection must be both fast and operationally …

Xunzhuo Liu, Bowei He, Xue Liu, Andy Luo, Haichen Zhang, Huamin Chen

19 views Mar 16

Academic · 1 min

Adaptive Vision-Language Model Routing for Computer Use Agents

arXiv:2603.12823v1 Announce Type: new Abstract: Computer Use Agents (CUAs) translate natural-language instructions into Graphical User Interface (GUI) actions such as clicks, keystrokes, and scrolls by …

Xunzhuo Liu, Bowei He, Xue Liu, Andy Luo, Haichen Zhang, Huamin Chen

7 views Mar 16

Xunzhuo Liu, Bowei He, Xue Liu, Andy Luo, Haichen Zhang, Huamin Chen

Articles by Xunzhuo Liu, Bowei He, Xue Liu, Andy Luo, Haichen Zhang, Huamin Chen

Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents

98$\times$ Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for …

Adaptive Vision-Language Model Routing for Computer Use Agents

JCG, PC

HSOLLC Co., Ltd.