Multi-agent Architecture Search via Agentic Supernet

• URL: http://arxiv.org/abs/2502.04180v2
• Date: Mon, 09 Jun 2025 05:15:47 GMT
• Title: Multi-agent Architecture Search via Agentic Supernet
• Authors: Guibin Zhang, Luyang Niu, Junfeng Fang, Kun Wang, Lei Bai, Xiang Wang,
• Abstract summary: Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents.<n>Despite the availability of methods to automate the design of agentic, they typically seek to identify a static, complex, one-size-fits-all system.<n>We introduce MaAS, an automated framework that samples query-dependent agentic systems from the supernet.
• Score: 17.235963703597093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing these systems often requires labor-intensive manual designs. Despite the availability of methods to automate the design of agentic workflows, they typically seek to identify a static, complex, one-size-fits-all system, which, however, fails to dynamically allocate inference resources based on the difficulty and domain of each query. To address this challenge, we shift away from the pursuit of a monolithic agentic system, instead optimizing the \textbf{agentic supernet}, a probabilistic and continuous distribution of agentic architectures. We introduce MaAS, an automated framework that samples query-dependent agentic systems from the supernet, delivering high-quality solutions and tailored resource allocation (\textit{e.g.}, LLM calls, tool calls, token cost). Comprehensive evaluation across six benchmarks demonstrates that MaAS \textbf{(I)} requires only $6\sim45\%$ of the inference costs of existing handcrafted or automated multi-agent systems, \textbf{(II)} surpasses them by $0.54\%\sim11.82\%$, and \textbf{(III)} enjoys superior cross-dataset and cross-LLM-backbone transferability.

Related papers

• RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory [57.449129198822476]
  RCR is a role-aware context routing framework for multi-agent large language model (LLM) systems.<n>It dynamically selects semantically relevant memory subsets for each agent based on its role and task stage.<n>A lightweight scoring policy guides memory selection, and agent outputs are integrated into a shared memory store.
  arXiv  Detail & Related papers  (2025-08-06T21:59:34Z)
• MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines [23.407716896592383]
  We propose a finite state machine based framework that can automatically generate a multi-agent system.<n>Given a task description, MetaAgent will design a multi-agent system and polish it through an optimization algorithm.<n>When the multi-agent system is deployed, the finite state machine will control the agent's actions and the state transitions.
  arXiv  Detail & Related papers  (2025-07-30T12:22:30Z)
• AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction [70.60422261117816]
  We propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.<n>Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection, which enables each agent to selectively access relevant information from any previous step.
  arXiv  Detail & Related papers  (2025-06-21T18:34:43Z)
• AutoData: A Multi-Agent System for Open Web Data Collection [37.832257245199365]
  AutoData is a novel multi-agent system for Automated web Data collection that requires minimal human intervention.<n>Instruct2DS is a new benchmark dataset supporting live data collection from web sources across three domains: academic, finance, and sports.
  arXiv  Detail & Related papers  (2025-05-21T04:32:35Z)
• Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems [50.29939179830491]
  Failure attribution in LLM multi-agent systems remains underexplored and labor-intensive. We develop and evaluate three automated failure attribution methods, summarizing their corresponding pros and cons. The best method achieves 53.5% accuracy in identifying failure-responsible agents but only 14.2% in pinpointing failure steps.
  arXiv  Detail & Related papers  (2025-04-30T23:09:44Z)
• OmniNova:A General Multimodal Agent Framework [0.5439020425819]
  Large Language Models (LLMs) with specialized tools presents new opportunities for intelligent automation systems. We present OmniNova, a modular multi-agent automation framework that combines language models with specialized tools such as web search, crawling, and code execution capabilities.
  arXiv  Detail & Related papers  (2025-03-25T19:21:01Z)
• Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation [58.799397354312596]
  Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks. Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation. In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges.
  arXiv  Detail & Related papers  (2025-02-18T03:20:50Z)
• G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks [14.024988515071431]
  We introduce G-Designer, an adaptive, efficient, and robust solution for multi-agent deployment.<n>G-Designer dynamically designs task-aware, customized communication topologies.
  arXiv  Detail & Related papers  (2024-10-15T17:01:21Z)
• Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems [42.137278756052595]
  $texttAgentPrune$ can seamlessly integrate into mainstream multi-agent systems. textbf(I) integrates seamlessly into existing multi-agent frameworks with $28.1%sim72.8%downarrow$ token reduction. textbf(III) successfully defend against two types of agent-based adversarial attacks with $3.5%sim10.8%uparrow$ performance boost.
  arXiv  Detail & Related papers  (2024-10-03T14:14:31Z)
• On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents [58.79302663733703]
  Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents.<n>However, the impact of clumsy or even malicious agents, on the overall performance of the system remains underexplored.<n>This paper investigates what is the resilience of various system structures under faulty agents.
  arXiv  Detail & Related papers  (2024-08-02T03:25:20Z)
• A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration [55.35849138235116]
  We propose automatically selecting a team of agents from candidates to collaborate in a dynamic communication structure toward different tasks and domains. Specifically, we build a framework named Dynamic LLM-Powered Agent Network ($textDyLAN$) for LLM-powered agent collaboration. We demonstrate that DyLAN outperforms strong baselines in code generation, decision-making, general reasoning, and arithmetic reasoning tasks with moderate computational cost.
  arXiv  Detail & Related papers  (2023-10-03T16:05:48Z)
• Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration [71.95914457415624]
  Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. We propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines.
  arXiv  Detail & Related papers  (2022-11-29T17:10:24Z)
• Utilizing Redundancy in Cost Functions for Resilience in Distributed Optimization and Learning [1.8414221462731502]
  This paper considers the problem of resilient distributed optimization and machine learning in a server-based architecture. The system comprises a server and multiple agents, where each agent has a local cost function. We consider the case when some of the agents may be asynchronous and/or Byzantine faulty.
  arXiv  Detail & Related papers  (2021-10-21T02:41:19Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical Systems [3.9599054392856488]
  quadratic analysis is challenging in Multi-Agent Reinforcement Learning (MARL) We propose a MARL algorithm based on the construction of an auxiliary single-agent LQ problem. We show that our algorithm provides a $tildeO(sqrtT)$ regret bound.
  arXiv  Detail & Related papers  (2020-01-27T23:37:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.