[2605.22502] Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost

-->

Computer Science > Artificial Intelligence

arXiv:2605.22502 (cs)

[Submitted on 21 May 2026]

Title:Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost

Authors:Simon Dennis, Rivaan Patil, Kevin Shabahang, Hao Guo<br>View a PDF of the paper titled Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost, by Simon Dennis and 3 other authors

View PDF<br>HTML (experimental)

Abstract:Agent orchestration frameworks have proliferated, collectively exceeding 290,000 GitHub stars across LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, Semantic Kernel, Strands, and LlamaIndex. All follow the same pattern: an external orchestrator above the LLM, injecting instructions and routing decisions every turn. Recent work has shown this architecture is dominated for procedural tasks by simply providing the procedure in a frontier model's system prompt [Dennis et al., 2026a], at the cost of consuming the context window, requiring a frontier model for every conversation, and exposing proprietary procedures to third-party providers. Compiling the procedure into the weights of a small fine-tuned model -- creating a subterranean agent -- should resolve all of these concerns, and prior work (SimpleTOD, FireAct, SynTOD, WorkflowLLM, Agent Lumos) has shown the technique works. Yet developer adoption has overwhelmingly favored orchestration. We identify three perceived barriers and address each empirically across travel booking (14 nodes), Zoom support (14 nodes, product-specific knowledge), and insurance claims (55 nodes, 6 decision hubs).

Comments:<br>19 pages

Subjects:

Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as:<br>arXiv:2605.22502 [cs.AI]

(or<br>arXiv:2605.22502v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.22502

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Simon Dennis [view email]<br>[v1]<br>Thu, 21 May 2026 13:54:11 UTC (96 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost, by Simon Dennis and 3 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.AI

next >

new<br>recent<br>| 2026-05

Change to browse by:

cs<br>cs.LG

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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?)

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? |<br>Disable MathJax (What is MathJax?)