Skip to content
AI News HubLIVE
Original source2 min read

From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators

Summary

Large language models (LLMs) excel at many tasks but often lack structural consistency in their solutions. A new approach called MetaFlow treats workflow generation as a meta-learning problem, training LLMs to compose solution strategies using a two-stage process: supervised fine-tuning on synthetic workflows, followed by reinforcement learning with verifiable rewards. MetaFlow achieves strong performance on in-domain tasks and demonstrates remarkable zero-shot generalization to out-of-domain tasks and novel operator sets.

SourcearXiv Machine LearningAuthor: Gan Luo, Zihan Qin, Bin Dong, Wotao Yin
From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 29 Jun 2026]

Title:From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators

View a PDF of the paper titled From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators, by Gan Luo and 3 other authors

View PDF HTML (experimental)

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.

Comments: 35 pages, 8 figures

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

Cite as: arXiv:2606.30704 [cs.LG]

(or arXiv:2606.30704v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.30704

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Gan Luo [view email] [v1] Mon, 29 Jun 2026 14:17:09 UTC (256 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators, by Gan Luo and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-06

Change to browse by:

cs cs.AI cs.CL

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • MetaFlow casts workflow generation as meta-learning, enabling LLMs to learn task-level algorithmic patterns.
  • It uses a two-stage training pipeline: supervised fine-tuning on synthetic data, then reinforcement learning with execution feedback.
  • Achieves state-of-the-art performance on QA, code generation, and math reasoning benchmarks with single inference.
  • Demonstrates strong zero-shot generalization to untrained tasks and novel operator sets.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models

From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators | AI News Hub