Related papers: Small Model as Master Orchestrator: Learning Unifi…

Multi-agent systems (MAS) have emerged as a promising approach for enhancing the reasoning capabilities of large language models in complex problem-solving; however, current MAS frameworks suffer from poor flexibility and scalability with…

In this paper, we propose a framework for solving a single-agent task by using multiple agents, each focusing on different aspects of the task. This approach has two main advantages: 1) it allows for training specialized agents on different…

Recent advances in LLM Multi-Agent Systems enable scalable orchestration of sub-agents, each coordinating hundreds or thousands of tools or Model Context Protocol (MCP) servers. However, existing retrieval methods typically match queries…

The proliferation of large language models (LLMs) and modular skills has endowed autonomous agents with increasingly powerful capabilities. Existing frameworks typically rely on monolithic LLMs and fixed logic to interface with these…

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…

The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…

Tool learning is increasingly important for large language models (LLMs) to effectively coordinate and utilize a diverse set of tools in order to solve complex real-world tasks. By selecting and integrating appropriate tools, LLMs extend…

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon…

Deep reinforcement learning algorithms have recently been used to train multiple interacting agents in a centralised manner whilst keeping their execution decentralised. When the agents can only acquire partial observations and are faced…

Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result…

While large language model-based multi-agent systems have shown strong potential for complex reasoning, how to effectively organize multiple agents remains an open question. In this paper, we introduce OrgAgent, a company-style hierarchical…

As future tasks in networked systems are increasingly relying on collaborative execution among distributed devices, trust has become an essential tool for securing both reliable collaborators and task-specific resources. However, the…

We consider a multi-agent reinforcement learning problem where each agent seeks to maximize a shared reward while interacting with other agents, and they may or may not be able to communicate. Typically the agents do not have access to…

LLM-based multi-agent systems (MAS) have emerged as a promising approach to tackle complex tasks that are difficult for individual LLMs. A natural strategy is to scale performance by increasing the number of agents; however, we find that…

Multi-robot manipulation tasks involve various control entities that can be separated into dynamically independent parts. A typical example of such real-world tasks is dual-arm manipulation. Learning to naively solve such tasks with…

Agentic AI systems represent a new frontier in artificial intelligence, where agents often based on large language models(LLMs) interact with tools, environments, and other agents to accomplish tasks with a degree of autonomy. These systems…

Adaptive orchestration of heterogeneous agents requires making sequential delegation decisions under uncertain and evolving agent behaviour, e.g., coordinating specialised AI models with varying reliability, cost, and response quality.…

Multi-agent systems are increasingly widespread in a range of application domains, with optimization and learning underpinning many of the tasks that arise in this context. Different approaches have been proposed to enable the cooperative…

Intelligent agent systems in real-world agricultural scenarios must handle diverse tasks under multimodal inputs, ranging from lightweight information understanding to complex multi-step execution. However, most existing approaches rely on…

LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules, while agents are rarely optimized through a unified reinforcement learning interface.…