3 papers
cs.RO2026
When Does Test-Time Physical Diagnosis Pay? A Frozen Policy Buys Evidence It Never Reads
Zhengshu Zhang
When a robot faces unfamiliar physical conditions, a common approach is to collect evidence about what changed and adapt. For such diagnosis to improve behavior, six ordered empiri…
cs.AI2026
ARC-Bench: Closed-Loop Replanning Masks Broken Action Ranking in Frozen JEPA World Models
Zhengshu Zhang, Zhiyuan Li
Reward-free latent world models plan by scoring candidate actions with distances in a frozen latent space: an action is preferred if its predicted future embedding lands closer to…
cs.CR2026
Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime Layer
Zhengsong Zhang, Zongze Li, Jiawei Guo +1
Local LLM agents such as OpenClaw and Nanobot run on end-user machines and act on host resources - the shell, filesystem, browser, stored credentials, and messaging applications -…