paper-with-me

Papers

EvoFlow: Evolving Diverse Agentic Workflows On The Fly

2025-02-11 · Guibin Zhang, Kaijie Chen, Guancheng Wan, Heng Chang, Hong Cheng, Kun Wang, Shuyue Hu, Lei Bai

The past two years have witnessed the evolution of large language model (LLM)-based multi-agent systems from labor-intensive manual design to partial automation (\textit{e.g.}, prompt engineering, communication topology) and eventually to fully automated design. However, existing agentic automation pipelines often lack LLM heterogeneity and focus on single-objective performance optimization, limiting their potential to combine weaker models for more customized and cost-effective solutions. To address this challenge, we propose EvoFlow, a niching evolutionary algorithm-based framework to automatically search a population of heterogeneous and complexity-adaptive agentic workflows, rather than a single homogeneous, complex workflow. Technically, EvoFlow performs \textit{(1) tag-based retrieval} to extract parent workflows from an agentic population, evolves new workflows through \textit{(2) crossover} and \textit{(3) mutation}, and employs \textit{(4) niching-based selection} to maintain population diversity and quality. Extensive evaluations across seven benchmarks demonstrate that EvoFlow is: \textbf{(I) diverse}, evolving a population of workflows ranging from simple I/O tasks to complex multi-turn interactions; \textbf{(II) high-performing}, outperforming previous handcrafted and automated workflows by $1.23\%\sim29.86\%$; \textbf{(III) economical}, surpassing powerful \llmname{o1-preview} at $12.4\%$ of its inference cost using weaker open-source models.

📄 PDF Abstract BibTeX arXiv:2502.07373

Code (0)

등록된 구현이 없습니다.

Tasks

Large Language ModelPrompt EngineeringTAG

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Grammar-based evolutionary approach for automated workflow composition with domain-specific operators and ensemble diversity

2024-02-03 · Rafael Barbudo, Aurora Ramírez, José Raúl Romero

The process of extracting valuable and novel insights from raw data involves a series of complex steps. In the realm of Automated Machine Learning (AutoML), a significant research focus is on automating aspects of this p…

AutoMLDiversity

EvoFlows: Evolutionary Edit-Based Flow-Matching for Protein Engineering

2026-03-12 · Nicolas Deutschmann, Constance Ferragu, Jonathan D. Ziegler, Shayan Aziznejad 외 arxiv

We introduce EvoFlows, a variable-length protein sequence-to-sequence modeling approach designed for protein engineering. Existing protein language models are poorly suited for optimization tasks: autoregressive models r…

SEW: Self-Evolving Agentic Workflows for Automated Code Generation

2025-05-24 · Siwei Liu, Jinyuan Fang, Han Zhou, Yingxu Wang 외

Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenges, existing research has focused on crafting multi-agent systems with agentic …

Code Generation

A co-evolving agentic AI system for medical imaging analysis

2025-09-24 · Songhao Li, Jonathan Xu, Tiancheng Bao, Yuxuan Liu 외 arxiv

Agentic AI is rapidly advancing in healthcare and biomedical research. However, in medical image analysis, their performance and adoption remain limited due to the lack of a robust ecosystem, insufficient toolsets, and t…

Active Learning

AgenticRed: Evolving Agentic Systems for Red-Teaming

2026-01-20 · Jiayi Yuan, Jonathan Nöther, Natasha Jaques, Goran Radanović arxiv

While recent automated red-teaming methods show promise for systematically exposing model vulnerabilities, most existing approaches rely on human-specified workflows. This dependence on manually designed workflows suffer…