Related papers: AgentGuard: Repurposing Agentic Orchestrator for S…
Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…
Large language model (LLM) agents execute tasks through multi-step workflows that combine planning, memory, and tool use. While this design enables autonomy, it also expands the attack surface for backdoor threats. Backdoor triggers…
Most safety testing efforts for large language models (LLMs) today focus on evaluating foundation models. However, there is a growing need to evaluate safety at the application level, as components such as system prompts, retrieval…
The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…
Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decision-making by combining the LLM outputs with results…
Agentic systems powered by Large Language Models (LLMs) have demonstrated remarkable potential in tackling complex, long-horizon tasks. However, their efficacy is fundamentally constrained by static configurations governing agent behaviors,…
In today's digital world, casual user-generated content often contains subtle cues that may inadvertently expose sensitive personal attributes. Such risks underscore the growing importance of effective text anonymization to safeguard…
This paper presents a novel approach to evaluating the security of large language models (LLMs) against prompt leakage-the exposure of system-level prompts or proprietary configurations. We define prompt leakage as a critical threat to…
Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…
The rapid proliferation of LLM agent frameworks has forced developers to choose between vendor lock-in through provider-specific SDKs and complex multi-package ecosystems that obscure control flow and hinder reproducibility. Integrating…
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 awareness and transparency in risk diagnosis. To introduce…
Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…
LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal…
The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…
Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…
Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the…
LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing…
We introduce QualityFlow, a dynamic agentic workflow for program synthesis. Given the English description of a programming problem and a set of unit tests, the model's goal is to synthesize the correct program that solves the problem and…
Agentic systems based on large language models (LLMs) operate not merely as text generators but as autonomous entities that dynamically retrieve information and invoke tools. This execution model shifts the attack surface from traditional…
The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…