AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models

• URL: http://arxiv.org/abs/2510.02669v1
• Date: Fri, 03 Oct 2025 01:57:07 GMT
• Title: AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
• Authors: Bo Ma, Hang Li, ZeHua Hu, XiaoFan Gui, LuYao Liu, Simon Liu,
• Abstract summary: AutoMaAS is a self-evolving multi-agent architecture search framework.<n>It uses neural architecture search principles to automatically discover optimal agent configurations.<n>It achieves 1.0-7.1% performance improvement and reduces inference costs by 3-5% compared to state-of-the-art methods.
• Score: 4.720605681761044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent systems powered by large language models have demonstrated remarkable capabilities across diverse domains, yet existing automated design approaches seek monolithic solutions that fail to adapt resource allocation based on query complexity and domain requirements. This paper introduces AutoMaAS, a self-evolving multi-agent architecture search framework that leverages neural architecture search principles to automatically discover optimal agent configurations through dynamic operator lifecycle management and automated machine learning techniques. Our approach incorporates four key innovations: (1) automatic operator generation, fusion, and elimination based on performance-cost analysis, (2) dynamic cost-aware optimization with real-time parameter adjustment, (3) online feedback integration for continuous architecture refinement, and (4) enhanced interpretability through decision tracing mechanisms. Extensive experiments across six benchmarks demonstrate that AutoMaAS achieves 1.0-7.1\% performance improvement while reducing inference costs by 3-5\% compared to state-of-the-art methods. The framework shows superior transferability across datasets and LLM backbones, establishing a new paradigm for automated multi-agent system design in the era of large language models.

Related papers

• AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms [22.971467368498452]
  We introduce AutoEP, a novel framework that bypasses training entirely by leveraging Large Language Models (LLMs) as zero-shot reasoning engines for algorithm control.<n>AutoEP consistently outperforms state-of-the-art tuning methods.
  arXiv  Detail & Related papers  (2025-09-27T08:45:21Z)
• Dynamic Acoustic Model Architecture Optimization in Training for ASR [51.21112094223223]
  DMAO is an architecture optimization framework that employs a grow-and-drop strategy to automatically reallocate parameters during training.<n>We evaluate DMAO through experiments with CTC onSpeech, TED-LIUM-v2 and Switchboard datasets.
  arXiv  Detail & Related papers  (2025-06-16T07:47:34Z)
• AutoMind: Adaptive Knowledgeable Agent for Automated Data Science [70.33796196103499]
  Large Language Model (LLM) agents have shown great potential in addressing real-world data science problems.<n>Existing frameworks depend on rigid, pre-defined and inflexible coding strategies.<n>We introduce AutoMind, an adaptive, knowledgeable LLM-agent framework.
  arXiv  Detail & Related papers  (2025-06-12T17:59:32Z)
• AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs [24.403284945948272]
  AutoJudger is an agent-driven framework for efficient and adaptive benchmarking of multimodal large language models.<n>AutoJudger employs the Item Response Theory (IRT) to estimate the question difficulty and an autonomous evaluation agent to dynamically select the most informative test questions.
  arXiv  Detail & Related papers  (2025-05-27T16:17:15Z)
• OmniNova:A General Multimodal Agent Framework [0.5439020425819]
  Large Language Models (LLMs) with specialized tools presents new opportunities for intelligent automation systems.<n>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)
• ZeroLM: Data-Free Transformer Architecture Search for Language Models [54.83882149157548]
  Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity.<n>This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics.<n>Our evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark.
  arXiv  Detail & Related papers  (2025-03-24T13:11:22Z)
• AutoTM 2.0: Automatic Topic Modeling Framework for Documents Analysis [0.17999333451993949]
  AutoTM 2.0 is a framework for optimizing additively regularized topic models. We show that AutoTM 2.0 achieves better performance compared to the previous AutoTM.
  arXiv  Detail & Related papers  (2024-10-01T13:13:15Z)
• AutoM3L: An Automated Multimodal Machine Learning Framework with Large Language Models [6.496539724366041]
  We introduce AutoM3L, an innovative Automated Multimodal Machine Learning framework. AutoM3L comprehends data modalities and selects appropriate models based on user requirements. We evaluate the performance of AutoM3L on six diverse multimodal datasets.
  arXiv  Detail & Related papers  (2024-08-01T16:01:51Z)
• AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving [68.73885845181242]
  We propose an Automatic Data Engine (AIDE) that automatically identifies issues, efficiently curates data, improves the model through auto-labeling, and verifies the model through generation of diverse scenarios. We further establish a benchmark for open-world detection on AV datasets to comprehensively evaluate various learning paradigms, demonstrating our method's superior performance at a reduced cost.
  arXiv  Detail & Related papers  (2024-03-26T04:27:56Z)
• AutoMix: Automatically Mixing Language Models [62.51238143437967]
  Large language models (LLMs) are now available from cloud API providers in various sizes and configurations.<n>We present Automix, an approach that strategically routes queries to larger LMs, based on the approximate correctness of outputs from a smaller LM.
  arXiv  Detail & Related papers  (2023-10-19T17:57:39Z)
• Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL [53.40030379661183]
  Auto-PyTorch is a framework to enable fully automated deep learning (AutoDL) It combines multi-fidelity optimization with portfolio construction for warmstarting and ensembling of deep neural networks (DNNs) We show that Auto-PyTorch performs better than several state-of-the-art competitors on average.
  arXiv  Detail & Related papers  (2020-06-24T15:15:17Z)

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.