Related papers: ChainCaps: Composition-Safe Tool-Using Agents via …

Multi-agent LLM systems have demonstrated impressive capabilities in complex collaborative tasks, yet most frameworks treat communication as instantaneous and free, overlooking a fundamental constraint in real world teamwork, collaboration…

Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for…

Autonomous systems are increasingly deployed in real-world environments, where they must achieve high performance while maintaining safety under state and input constraints. Although Model Predictive Control (MPC) provides a principled…

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…

Knowledge graphs provide structured context for multi-hop question answering, but deployed systems must balance answer accuracy with strict latency and cost targets while preserving provenance. Static k-hop expansions and "think-longer"…

Multi-turn tool-calling LLMs (models capable of invoking external APIs or tools across several user turns) have emerged as a key feature in modern AI assistants, enabling extended dialogues from benign tasks to critical business, medical,…

Network Intrusion Detection Systems (NIDS) have been studied in research for almost four decades. Yet, despite thousands of papers claiming scientific advances, a non-negligible number of recent works suggest that the findings of prior…

Large language models (LLMs) are increasingly deployed in agentic systems, where a fundamental task is mapping user intents to relevant external tools. Errors in tool selection can have severe outcomes, such as unauthorized data access,…

The software supply chain attacks are becoming more and more focused on trusted development and delivery procedures, so the conventional post-build integrity mechanisms cannot be used anymore. The available frameworks like SLSA, SBOM and in…

Deep reinforcement learning has emerged as a powerful tool for obtaining high-performance policies. However, the safety of these policies has been a long-standing issue. One promising paradigm to guarantee safety is a shield, which shields…

We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interprets natural language tasks and executes protocol-compliant actions on…

Developers rely on constant-time programming to prevent timing side-channel attacks. But these efforts can be undone by compilers, whose optimizations may silently reintroduce leaks. While recent works have measured the extent of such…

A natural way for cooperative tasking in multi-agent systems is through a top-down design by decomposing a global task into sub-tasks for each individual agent such that the accomplishments of these sub-tasks will guarantee the achievement…

AI agents dynamically acquire tools, orchestrate sub-agents, and transact across organizational boundaries, yet no existing security layer verifies what an agent can do, whether it executed what it claims, or what happened in a multi-agent…

Why do language agents fail on tasks they are capable of solving? We argue that many such failures are reliability failures caused by stochastic drift from a task's latent solution structure, not capability failures. Every well-defined…

Tool-using LLM agents produce trajectories whose calls form a directed dependency graph: earlier tool outputs supply arguments to later calls. Whether this execution structure is represented inside the model is unknown; prior structural…

Machine-learned interatomic potentials (MLIPs) are deployed for high-throughput materials screening without formal reliability guarantees. We show that a single MLIP used as a stability filter misses 93% of density functional theory…

A shield is attached to a system to guarantee safety by correcting the system's behavior at runtime. Existing methods that employ design-time synthesis of shields do not scale to multi-agent systems. Moreover, such shields are typically…

This paper introduces a run-time mechanism for preventing leakage of secure information in distributed systems. We consider a general concurrency language model, where concurrent objects interact by asynchronous method calls and futures.…

Model Context Protocol (MCP) has become a key infrastructure for connecting LLMs with external tools, scaling to 10,000+ MCP servers with diverse tools. Unfortunately, there is still a large gap between real-world MCP usage and current…