From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators
- URL: http://arxiv.org/abs/2606.30704v1
- Date: Mon, 29 Jun 2026 14:17:09 GMT
- Title: From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators
- Abstract summary: Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed for reliable deployment.<n>We present MetaFlow, which casts workflow generation as a meta-learning problem.<n>It trains in two stages: supervised fine-tuning on synthetic workflow data, followed by reinforcement learning with verifiable rewards.<n>The resulting model produces effective for trained tasks and exhibits strong generalization to untrained tasks and novel operator sets.
- Score: 17.263246226058474
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed for reliable deployment. Workflows that encode recurring algorithmic patterns at the task level provide a principled framework, offering robustness across instance variations, interpretable traces for debugging, and reusability across problem instances. However, manually designing such workflows requires significant expertise and effort, limiting their broader application. While automatic workflow generation could address this bottleneck, existing methods either produce instance-specific solutions without learning task-level patterns, or cannot generalize beyond their training configurations. We present MetaFlow, which casts workflow generation as a meta-learning problem: given a task and an operator set, the model learns to compose solution strategies. MetaFlow trains in two stages: supervised fine-tuning on synthetic workflow data, followed by reinforcement learning with verifiable rewards (RLVR) that uses execution feedback across problem instances in the task to improve end-to-end success. The resulting model produces effective workflows for trained tasks and exhibits strong generalization to untrained tasks and novel operator sets. Across benchmarks in question answering, code generation, and mathematical reasoning, MetaFlow achieves performance comparable to state-of-the-art baselines on in-domain tasks with single inference, while demonstrating remarkable zero-shot generalization capabilities on out-of-domain tasks and operator sets.
Related papers
- From Specification to Execution: AI Assisted Scientific Workflow Management [0.7507031378170735]
We present an AI-assisted approach to scientific workflow management.<n>The method introduces a structured specification phase that separates workflow intent, design, and implementation, allowing validation prior to code generation.<n>We evaluate the approach using a federated learning workflow for medical imaging, chosen for its parallel, iterative, and dependency-intensive structure.
arXiv Detail & Related papers (2026-06-16T19:21:09Z) - FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning [5.153212048436295]
LLMs can solve complex tasks through reasoning and tool use, but accurately translating these solutions into structured remains challenging.<n>We model as sequences of tool use and reformulate the problem as designing a mechanism that can both solve tasks and reliably construct them.<n>We propose an Execute-Summarize(ES) framework that decouples task execution from workflow construction.
arXiv Detail & Related papers (2026-02-12T10:04:42Z) - Learning to Compose for Cross-domain Agentic Workflow Generation [56.630382886594184]
We create an open-source LLM for cross-domain workflow generation.<n>We learn a compact set of reusable workflow capabilities across diverse domains.<n>Our 1-pass generator surpasses SOTA refinement baselines that consume 20 iterations.
arXiv Detail & Related papers (2026-02-11T18:27:22Z) - DyFlow: Dynamic Workflow Framework for Agentic Reasoning [79.19799197382478]
DyFlow is a dynamic workflow generation framework that adaptively constructs and adjusts reasoning procedures based on task requirements and real-time intermediate feedback.<n>We systematically evaluate DyFlow across diverse domains, including social reasoning, biomedical tasks, mathematical problem solving, and code generation.<n>Results demonstrate that DyFlow significantly outperforms existing baselines, achieving substantial Pass@k improvements and exhibiting robust generalization across diverse domains.
arXiv Detail & Related papers (2025-09-30T10:36:23Z) - Learning Task Representations from In-Context Learning [67.66042137487287]
Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning (ICL)<n>We introduce an automated formulation for encoding task information in ICL prompts as a function of attention heads.<n>The proposed method successfully extracts task-specific information from in-context demonstrations and excels in both text and regression tasks.
arXiv Detail & Related papers (2025-02-08T00:16:44Z) - Flow: Modularized Agentic Workflow Automation [53.073598156915615]
Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution.<n>However, the effective adjustment of agentic during execution has not been well studied.<n>In this paper, we define an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by agents.<n>Our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance.
arXiv Detail & Related papers (2025-01-14T04:35:37Z) - Benchmarking Agentic Workflow Generation [80.74757493266057]
We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>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) - Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data.
For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
arXiv Detail & Related papers (2023-11-23T15:46:54Z)
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.