4 citations · 7 across the 5 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.CR2026
ZoneClaw: Mitigating Persistent Memory Attacks by Establishing Memory-Zoning in OpenClaw-Style Computer-Use Agents
Haokai Ma, Chieh Lin, Yupeng Qiu +1
Computer-use agents increasingly operate as long-running assistants through persistent workspace memory, which OpenClaw-style CUAs realize as automatically reloaded files that hold…
cs.CR2026
Misleading the Planner through Deceptive Resumes: Registration-Time Injection in Centralized Multi-Agent Systems
Zhaofeng Yu, Haokai Ma, Dongyang Zhan +3
A centralized LLM-based multi-agent system (MAS) extends its functionality by registering new worker agents, whose descriptions are read by the planner to decide how a task is deco…
cs.LG2026
Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains
Haokai Ma, Lee Yan Zhen, Gang Yang +4
Large language models are increasingly deployed in high-stakes domains, where confident yet incorrect inferences may cause severe real-world harm, bringing the long-overlooked issu…