AFlow: Automating Agentic Workflow Generation

• URL: http://arxiv.org/abs/2410.10762v1
• Date: Mon, 14 Oct 2024 17:40:40 GMT
• Title: AFlow: Automating Agentic Workflow Generation
• Authors: Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xionghui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, Bingnan Zheng, Bang Liu, Yuyu Luo, Chenglin Wu,
• Abstract summary: Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains. We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search. Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines.
• Score: 36.61172223528231
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformulate workflow optimization as a search problem over code-represented workflows, where LLM-invoking nodes are connected by edges. We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search, iteratively refining workflows through code modification, tree-structured experience, and execution feedback. Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFlow enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars. The code will be available at https://github.com/geekan/MetaGPT.

Related papers

• Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning [6.328780056857816]
  gen-AI that involve multiple ML model calls, tool/API calls, data retrieval, or generic code execution are often tuned manually in an ad-hoc way. AdaSeek organizes workflow tuning methods into different layers based on the user-specified total search budget. Cognify improves these workflow's generation quality by up to 2.8x, reduces execution monetary cost by up to 10x, and reduces end-to-end latency by 2.7x.
  arXiv  Detail & Related papers  (2025-02-12T01:36:27Z)
• ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization [51.280919773837645]
  We develop ScoreFlow, a high-performance framework for agent workflow optimization. ScoreFlow incorporates Score-DPO, a novel variant of the direct preference optimization method that accounts for quantitative feedback. It achieves an 8.2% improvement over existing baselines across question answering, coding, and mathematical reasoning.
  arXiv  Detail & Related papers  (2025-02-06T18:47:49Z)
• Flow: A Modular Approach to Automated Agentic Workflow Generation [53.073598156915615]
  Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution. However, the effective adjustment of Agentic during execution has not been well-studied.
  arXiv  Detail & Related papers  (2025-01-14T04:35:37Z)
• Opus: A Large Work Model for Complex Workflow Generation [0.0]
  Opus is a framework for generating and optimizing tasks tailored to complex Business Process Outsourcing (BPO) use cases. Our approach generates executables from Intention, defined as the alignment of Client Input, Client Output and Process Directed Context.
  arXiv  Detail & Related papers  (2024-11-30T20:00:41Z)
• FlowTS: Time Series Generation via Rectified Flow [67.41208519939626]
  FlowTS is an ODE-based model that leverages rectified flow with straight-line transport in probability space. For unconditional setting, FlowTS achieves state-of-the-art performance, with context FID scores of 0.019 and 0.011 on Stock and ETTh datasets. For conditional setting, we have achieved superior performance in solar forecasting.
  arXiv  Detail & Related papers  (2024-11-12T03:03:23Z)
• WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models [105.46456444315693]
  We presentLLM, a data-centric framework to enhance the capability of large language models in workflow orchestration. It first constructs a large-scale fine-tuningBench with 106,763 samples, covering 1,503 APIs from 83 applications across 28 categories. LlamaLlama demonstrates a strong capacity to orchestrate complex APIs, while also achieving notable generalization performance.
  arXiv  Detail & Related papers  (2024-11-08T09:58:02Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorFBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures. We also present WorFEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms. We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• AutoFlow: Automated Workflow Generation for Large Language Model Agents [39.72700864347576]
  Large Language Models (LLMs) have shown significant progress in understanding complex natural language. To make sure LLM Agents follow an effective and reliable procedure to solve the given task, manually designed are usually used. We propose AutoFlow, a framework designed to automatically generate for agents to solve complex tasks.
  arXiv  Detail & Related papers  (2024-07-01T21:05:02Z)

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.