Related papers: GEMMAS: Graph-based Evaluation Metrics for Multi A…

Large Language Models (LLMs) are becoming increasingly powerful and capable of handling complex tasks, e.g., building single agents and multi-agent systems. Compared to single agents, multi-agent systems have higher requirements for the…

Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation,…

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…

Objective: Emergency medical dispatch (EMD) is a high-stakes process challenged by caller distress, ambiguity, and cognitive load. Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers. This…

Large Language Models (LLMs) have enabled collaborative Multi-Agent (MA) systems, where interacting agents improve performance through diverse reasoning and iterative refinement. However, these systems remain vulnerable to error…

There is an growing interest in using Large Language Models (LLMs) in multi-agent systems to tackle interactive real-world tasks that require effective collaboration and assessing complex situations. Yet, we still have a limited…

As large language models (LLMs) are increasingly used in multi-agent systems, questions of fairness should extend beyond resource distribution and procedural design to include the fairness of how agents communicate. Drawing from…

In this paper, we consider the problem of providing robustness to adversarial communication in multi-agent systems. Specifically, we propose a solution towards robust cooperation, which enables the multi-agent system to maintain high…

Multi-agent systems (MAS) often achieve higher reasoning accuracy than single models, but their reliance on repeated debates across agents makes them computationally expensive. We introduce SMAGDi, a distillation framework that transfers…

Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but their evaluations often collapse behavior into final task success. AgentAtlas reframes agent evaluation as a…

Language-driven grasp detection has the potential to revolutionize human-robot interaction by allowing robots to understand and execute grasping tasks based on natural language commands. However, existing approaches face two key challenges.…

Traditional model-based reinforcement learning approaches learn a model of the environment dynamics without explicitly considering how it will be used by the agent. In the presence of misspecified model classes, this can lead to poor…

Agents, as user-centric tools, are increasingly deployed for human task delegation, assisting with a broad spectrum of requests by generating thoughts, engaging with user proxies, and producing action plans. However, agents based on large…

Collaboration is crucial for reaching collective goals. However, its effectiveness is often undermined by the strategic behavior of individual agents -- a fact that is captured by a high Price of Stability (PoS) in recent literature [Blum…

As LLMs are increasingly deployed as agents, agentic reasoning - the ability to combine tool use, especially search, and reasoning - becomes a critical skill. However, it is hard to disentangle agentic reasoning when evaluated in complex…

The era of foundation models has revolutionized AI research, yet Graph Foundation Models (GFMs) remain constrained by the scarcity of large-scale graph corpora. Traditional graph data synthesis techniques primarily focus on simplistic…

Many real-world scenarios involve a team of agents that have to coordinate their policies to achieve a shared goal. Previous studies mainly focus on decentralized control to maximize a common reward and barely consider the coordination…

Automated Essay Scoring (AES) is crucial for modern education, particularly with the increasing prevalence of multimodal assessments. However, traditional AES methods struggle with evaluation generalizability and multimodal perception,…

In Multi-Agent Systems (MAS), agents are designed with social capabilities, allowing them to understand and reason about social concepts such as norms when interacting with others (e.g., inter-robot interactions). In Normative MAS (NorMAS),…

Large-scale social simulators are essential for studying complex social patterns. Prior work explores hybrid methods to scale up simulations, combining large language models (LLM)-based agents with numerical agent-based models (ABM).…