[2604.09718] Agentic Compilation: Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation

-->

Computer Science > Distributed, Parallel, and Cluster Computing

arXiv:2604.09718 (cs)

[Submitted on 8 Apr 2026 (v1), last revised 25 Apr 2026 (this version, v2)]

Title:Agentic Compilation: Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation

Authors:Jagadeesh Chundru<br>View a PDF of the paper titled Agentic Compilation: Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation, by Jagadeesh Chundru

View PDF<br>HTML (experimental)

Abstract:LLM-driven web agents operating through continuous inference loops -- repeatedly querying a model to evaluate browser state and select actions -- exhibit a fundamental scalability constraint for repetitive tasks. We characterize this as the Rerun Crisis: the linear growth of token expenditure and API latency relative to execution frequency. For a 5-step workflow over 500 iterations, a continuous agent incurs approximately 150.00 USD in inference costs; even with aggressive caching, this remains near 15.00 USD. We propose a Compile-and-Execute architecture that decouples LLM reasoning from browser execution, reducing per-workflow inference cost to under 0.10 USD. A one-shot LLM invocation processes a token-efficient semantic representation from a DOM Sanitization Module (DSM) and emits a deterministic JSON workflow blueprint. A lightweight runtime then drives the browser without further model queries. We formalize this cost reduction from O(M x N) to amortized O(1) inference scaling, where M is the number of reruns and N is the sequential actions. Empirical evaluation across data extraction, form filling, and fingerprinting tasks yields zero-shot compilation success rates of 80-94%. Crucially, the modularity of the JSON intermediate representation allows minimal Human-in-the-Loop (HITL) patching to elevate execution reliability to near-100%. At per-compilation costs between 0.002 USD and 0.092 USD across five frontier models, these results establish deterministic compilation as a paradigm enabling economically viable automation at scales previously infeasible under continuous architectures.

Comments:<br>12 pages, 4 figures, 2 tables. v2: Expanded literature review and clarified architecture limitations

Subjects:

Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Programming Languages (cs.PL)

ACM classes:<br>I.2.11; I.2.2

Cite as:<br>arXiv:2604.09718 [cs.DC]

(or<br>arXiv:2604.09718v2 [cs.DC] for this version)

https://doi.org/10.48550/arXiv.2604.09718

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Jagadeesh Chundru [view email]<br>[v1]<br>Wed, 8 Apr 2026 14:22:37 UTC (16 KB)

[v2]<br>Sat, 25 Apr 2026 21:50:26 UTC (17 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Agentic Compilation: Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation, by Jagadeesh Chundru<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.DC

next >

new<br>recent<br>| 2026-04

Change to browse by:

cs<br>cs.AI<br>cs.PL

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...