collaborators

7 papers

cs.CR2026

: Improving Agent Safety through Multi-Stage Defense

Zibo Xiao, Haoyu Wang, Jun Sun

Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks. However, risks may e…

cs.CR2026

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants

Haoyu Wang, Zibo Xiao, Yedi Zhang +2

LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the pot…

cs.AI2026

ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction

Haoyu Wang, Christopher M. Poskitt, Jiali Wei +1

Large Language Model (LLM) agents increasingly operate across domains such as robotics, virtual assistants, and web automation. However, their stochastic decision-making introduces…

cs.AI2026

Domain-Specialized Tree of Thought through Plug-and-Play Predictors

Xuanqi Gao, Haoyu Wang, Jun Sun +2

While Large Language Models (LLMs) have advanced complex reasoning, prominent methods like the Tree of Thoughts (ToT) framework face a critical trade-off between exploration depth…

cs.AI2026

Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correction

Tao Zhe, Haoyu Wang, Bo Luo +6

Tool invocation is a core capability of agentic systems, yet failures often arise not from individual tool calls but from how multiple tools are organized and executed together. Ex…

cs.CR2026

LLM-enabled Applications Require System-Level Threat Monitoring

Yedi Zhang, Haoyu Wang, Xianglin Yang +2

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, h…