Related papers: Reliable Self-Harm Risk Screening via Adaptive Mul…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Multi-component natural language processing (NLP) pipelines are increasingly deployed for high-stakes decisions, yet no existing adversarial method can test their robustness under realistic conditions: binary-only feedback, no gradient…

Large Language Models (LLMs) are increasingly applied in healthcare, yet ensuring their ethical integrity and safety compliance remains a major barrier to clinical deployment. This work introduces a multi-agent refinement framework designed…

Deep reinforcement learning in continuous domains focuses on learning control policies that map states to distributions over actions that ideally concentrate on the optimal choices in each step. In multi-agent navigation problems, the…

Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound. We identify a root cause shared by both major mitigation paradigms (agent-based debate and retrieval…

Large language model (LLM)-based agents are increasingly used to perform complex, multi-step workflows in regulated settings such as compliance and due diligence. However, many agentic architectures rely primarily on prompt engineering of a…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

With recent breakthroughs in large language models (LLMs) for reasoning, planning, and complex task generation, artificial intelligence systems are transitioning from isolated single-agent architectures to multi-agent systems with…

Large language models (LLMs) are increasingly used in clinical settings, raising concerns about racial bias in both generated medical text and clinical reasoning. Existing studies have identified bias in medical LLMs, but many focus on…

Modeling coordination among generative agents in complex multi-round decision-making presents a core challenge for AI and operations management. Although behavioral experiments have revealed cognitive biases behind supply chain…

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

Modeling latent clinical constructs from unconstrained clinical interactions is a unique challenge in affective computing. We present ADAPTS (Agentic Decomposition for Automated Protocol-agnostic Tracking of Symptoms), a framework for…

LLM-agent simulation offers a flexible computational tool for studying population response trajectories that depend on scenario events, memory, demographics, and evolving social context. However, full multi-round simulation scales linearly…

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…

Recent AI agents, such as ChatGPT and LLaMA, primarily rely on instruction tuning and reinforcement learning to calibrate the output of large language models (LLMs) with human intentions, ensuring the outputs are harmless and helpful.…

We study a sequential mechanism design problem in which a principal seeks to elicit truthful reports from multiple rational agents while starting with no prior knowledge of agents' beliefs. We introduce Distributionally Robust Adaptive…

Large Language Model (LLM) based multi-agent systems have shown remarkable performance in various tasks, especially when enhanced through collaborative communication. However, current methods often rely on a fixed number of agents and…

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…

Tool-using LLM agents face a reliability-cost tradeoff: routing every decision through the LLM improves correctness but incurs high latency and inference cost, while pre-coded workflow graphs reduce cost but become brittle under…

User authentication and fraud detection face growing challenges as digital systems expand and adversaries adopt increasingly sophisticated tactics. Traditional knowledge-based authentication remains rigid, requiring exact word-for-word…