3 papers
cs.CR2026
Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents
Zhuowen Liu
LLM agents increasingly screen tool outputs with small prompt-injection detectors, and teams choose among detectors by their scores on public benchmarks. We ask whether those score…
cs.LG2026
LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression
Zhuowen Liu, Longkun Hao, Shiyu Feng +3
The rapid growth in the parameter scale of large language models (LLMs) has created a strong demand for efficient compression techniques. As a hardware-agnostic and highly compatib…
cs.AI2026
HERALD: Counterfactual Audits and Minimal Repairs for Proof-of-Retrieval Rewards
Zhuowen Liu, Bohan Cui, YinShang Guo +2
Search-agent rewards mix answer quality, citation grounding, tool cost, and anti-hacking terms; a high score therefore need not imply that cited evidence was retrieved, and added p…