Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills
Hongliang Liu, Yuhao Wu, Tung-Ling Li
AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from marketplaces and other agents. Gov…
cs.CR2025
Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
Tung-Ling Li, Hongliang Liu
RLHF-style alignment trains language models to refuse unsafe requests, but how much operational margin does this refusal rest on? We introduce the refusal-affirmation logit gap: th…