相关论文: Invisible Orchestrators Suppress Protective Behavi…

Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working memory through their context window, which stores interaction…

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 shared resources to solve complex tasks. While such systems…

Harnessing the power of LLMs requires a delicate dance between being helpful and harmless. This creates a fundamental tension between two competing challenges: vulnerability to adversarial attacks that elicit unsafe content, and a tendency…

Autonomous agent systems are governed by enforcement mechanisms that flag hard constraint violations at runtime. The Agent Control Protocol identifies a structural limit of such systems: a correctly-functioning enforcement engine can enter…

Scaffolding Large Language Models (LLMs) into multi-agent systems often improves performance on complex tasks, but the safety impact of such scaffolds has not been thoroughly explored. We introduce AgentBreeder, a framework for…

We study multi-turn multi-agent orchestration, where multiple large language model (LLM) agents interact over multiple turns by iteratively proposing answers or casting votes until reaching consensus. Using four LLMs (Gemini 2.5 Pro, GPT-5,…

Multi-agent systems (MAS) powered by large language models (LLMs) increasingly adopt planner--executor architectures, where planners convert prompts into subtasks, roles, dependencies, and routing paths. This flexibility enables adaptive…

Large language model (LLM) agents with extended autonomy unlock new capabilities, but also introduce heightened challenges for LLM safety. In particular, an LLM agent may pursue objectives that deviate from human values and ethical norms, a…

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a…

The rapid evolution of Large Language Models (LLMs) has led to the emergence of Multi-Agent Systems where collective cooperation is often threatened by the "Tragedy of the Commons." This study investigates the effectiveness of Anchoring…

Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…

Invisible labor is work that is either not fully visible or not appropriately compensated. In open source software (OSS) ecosystems, essential tasks that do not involve code (like content moderation) often become invisible to the detriment…

As foundation models are increasingly deployed as interacting agents in multi-agent systems, their collective behavior raises new challenges for trustworthiness, transparency, and accountability. Traditional coordination mechanisms, such as…

Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges. However, within these multi-agent systems, the…

In multi-agent systems, agents observe data, and use them to make inferences and take actions. As a result sensing and control naturally interfere, more so from a real-time perspective. A natural consequence is that in multi-agent systems…

Autonomous agents powered by large language models (LLMs) enable novel use cases in domains where responsible action is increasingly important. Yet the inherent unpredictability of LLMs raises safety concerns about agent reliability. In…

Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings. However, the majority of existing methodologies for identifying biases in…

Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry. However, how to prevent these networks from generating malicious information…

Increased delegation of commercial, scientific, governmental, and personal activities to AI agents -- systems capable of pursuing complex goals with limited supervision -- may exacerbate existing societal risks and introduce new risks.…

Virtual environments are essential to AI agent research. Existing environments for LLM agent research typically focus on either physical task solving or social simulation, with the former oversimplifying agent individuality and social…