Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA
Wenlin Lin, Fanzhe Wei
Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents give one mo…
cs.AI2026
Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State
Fanzhe Wei, Li Liu
Runtime compression of serving state trades quality for capacity with no priced guarantee: systems adapt precision on load signals with no soundness statement, and certified approa…
cs.AI2026
Runtime Observability for Heterogeneous Attention Memory
Fanzhe Wei, Li Liu, Ziyang Wang +1
Modern models no longer keep a plain KV cache: latent caches, learned sparse selectors and recurrent states each carry the model's memory in a different form, and each fails differ…