Related papers: Multipath agents for modular multitask ML systems

Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently,…

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,…

The multitask diffusion LMS is an efficient strategy to simultaneously infer, in a collaborative manner, multiple parameter vectors. Existing works on multitask problems assume that all agents respond to data synchronously. In several…

Multi-agent systems (MAS) have shown great potential in executing complex tasks, but coordination and safety remain significant challenges. Multi-Agent Reinforcement Learning (MARL) offers a promising framework for agent collaboration, but…

Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…

Recent studies show that LLMs possess different skills and specialize in different tasks. In fact, we observe that their varied performance occur in several levels of granularity. For example, in the code optimization task, code LLMs excel…

Being engaging, knowledgeable, and empathetic are all desirable general qualities in a conversational agent. Previous work has introduced tasks and datasets that aim to help agents to learn those qualities in isolation and gauge how well…

Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood. We study when end-to-end RL training…

This paper presents a novel design of a multi-agent system framework that applies large language models (LLMs) to automate the parametrization of simulation models in digital twins. This framework features specialized LLM agents tasked with…

A complex system is made up of many components with many interactions. So the design of systems such as simulation systems, cooperative systems or assistance systems includes a very accurate modelling of interactional and communicational…

Generative agents, which implement behaviors using a large language model (LLM) to interpret and evaluate an environment, has demonstrated the capacity to solve complex tasks across many social and technological domains. However, when these…

Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In…

Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning methods to handle…

The problem of balancing conflicting needs is fundamental to intelligence. Standard reinforcement learning algorithms maximize a scalar reward, which requires combining different objective-specific rewards into a single number.…

In this paper, we propose a model for evaluating the transmission performance of multipath transport. Previous researches focused exclusively on single pair users in simple scenarios. The distinct perspective in this paper is to build…

Multi-agent Reinforcement Learning (MARL) problems often require cooperation among agents in order to solve a task. Centralization and decentralization are two approaches used for cooperation in MARL. While fully decentralized methods are…

This paper introduces Multi-Agent MDP Homomorphic Networks, a class of networks that allows distributed execution using only local information, yet is able to share experience between global symmetries in the joint state-action space of…

In recent developments within the research community, the integration of Large Language Models (LLMs) in creating fully autonomous agents has garnered significant interest. Despite this, LLM-based agents frequently demonstrate notable…

Load balancing across a networked environment is a monotonous job. Moreover, if the job to be distributed is a constraint satisfying one, the distribution of load demands core intelligence. This paper proposes parallel processing through…

Adaptive cooperation in multi-agent reinforcement learning (MARL) requires policies to express homogeneous, specialised, or mixed behaviours, yet achieving this adaptivity remains a critical challenge. While parameter sharing (PS) is…