12 papers
HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence
Xiqiao Xiong, Moxin Li, Zhixin Ma +4
Agent harnesses play a critical role in defenses by enforcing safety constraints to prevent unsafe actions. However, rapidly emerging attacks outpace manual harness adaptation, mot…
HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control
Zhuo Liu, Moxin Li, Zhixin Ma +3
Large language model (LLM) agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtime defenses that prevent unsafe…
What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents
Wenjie Wang, Wenhe Si, Xinyue Xu +1
Long-term memory enables personalized conversational agents to retain user information across sessions. However, existing memory architectures primarily optimize for utility while…
SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing
Tianyu Chen, Chujia Hu, Wenjie Wang
LLM agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a guard model that labels each pr…
MemoHarness: Agent Harnesses That Learn from Experience
Yue Huang, Wenjie Wang, Han Bao +7
An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools, orchestration, memory, decoding, and output handling. Whil…
From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space
Yue Xu, Yutao Sun, Yihao Liu +7
Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a cons…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…
Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents
Yongxiang Li, Moxin Li, Zhixin Ma +4
Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into external observations such as t…
Emergent Risks in Generative Multi-Agent Systems
Yue Huang, Yu Jiang, Wenjie Wang +12
Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate sh…
A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)
Tianyu Chen, Dongrui Liu, Xia Hu +2
Clawdbot is a self-hosted, tool-using personal AI agent with a broad action space spanning local execution and web-mediated workflows, which raises heightened safety and security c…
LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios
Tianyu Chen, Chujia Hu, Ge Gao +3
Computer-use agents (CUAs) execute multi-stage tasks through tools, where an early unsafe decision can propagate to consequential actions. Evaluating only final outcomes can miss s…
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Dongrui Liu, Qihan Ren, Chen Qian +40
The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk…