collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving

Xunzhuo Liu, Bowei He, Xue Liu +3

Production vLLM fleets typically provision each instance for the worst-case context length, leading to substantial KV-cache over-allocation and under-utilized concurrency. In pract…

cs.CL2026

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

Xunzhuo Liu, Bowei He, Xue Liu +3

Production AI agents frequently receive user-specific queries that are highly repetitive, with up to 47\% being semantically similar to prior interactions, yet each query is typica…

cs.CL2026

Adaptive Vision-Language Model Routing for Computer Use Agents

Xunzhuo Liu, Bowei He, Xue Liu +3

Computer Use Agents (CUAs) translate natural-language instructions into Graphical User Interface (GUI) actions such as clicks, keystrokes, and scrolls by relying on a Vision-Langua…

cs.CL2026

98 Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router

Xunzhuo Liu, Bowei He, Xue Liu +3

System-level routers that intercept LLM requests for safety classification, domain routing, and PII detection must be both fast and operationally lightweight: they should add minim…

cs.CL2026

Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems

Xunzhuo Liu, Bowei He, Xue Liu +2

Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source mate…