相关论文: Position: A Three-Layer Probabilistic Assume-Guara…
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…
Large language models (LLMs) are rapidly evolving into autonomous agents that cooperate across organizational boundaries, enabling joint disaster response, supply-chain optimization, and other tasks that demand decentralized expertise…
Current agentic AI architectures are fundamentally incompatible with the security and epistemological requirements of high-stakes scientific workflows. The problem is not inadequate alignment or insufficient guardrails, it is architectural:…
Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…
This position paper argues that securing LLM agents requires first defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user's intent. Modern LLM agents operate over an…
Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing…
Large Language Model (LLM) agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system's susceptibility to prompt injection and other forms of…
We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position, we conduct a systematic analysis of 59 academic papers, 21 production agent systems,…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…
This position paper argues that the field of LLM agents requires a unified, telecom-inspired communication protocol to ensure safety, interoperability, and scalability, especially within the context of Next Generation (NextG) networks.…
The rise of LLM-based agents shows great potential to revolutionize task planning, capturing significant attention. Given that these agents will be integrated into high-stake domains, ensuring their reliability and safety is crucial. This…
LLM-powered Multi-Agent Systems (LLM-MAS) unlock new potentials in distributed reasoning, collaboration, and task generalization but also introduce additional risks due to unguaranteed agreement, cascading uncertainty, and adversarial…
As LLM agents evolve into collaborative multi-agent systems, their memory requirements grow rapidly in complexity. This position paper frames multi-agent memory as a computer architecture problem. We distinguish shared and distributed…
AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…
Quantitative requirements play an important role in the context of multi-agent systems, where there is often a trade-off between the tasks of individual agents and the constraints that the agents must jointly adhere to. We study multi-agent…
Autonomous Artificial Intelligence (AI) agents, powered by Large Language Models (LLMs), advance rapidly toward interconnected systems -- an Internet of Agents (IoA). This vision enables complex problem-solving while introducing systemic…
AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…
As AI agents built on large language models (LLMs) become increasingly embedded in society, issues of coordination, control, delegation, and accountability are entangled with concerns over their reliability. To design and implement LLM…
Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…