[2605.26289] Stateful Inference for Low-Latency Multi-Agent Tool Calling

-->

Computer Science > Machine Learning

arXiv:2605.26289 (cs)

[Submitted on 25 May 2026]

Title:Stateful Inference for Low-Latency Multi-Agent Tool Calling

Authors:Victor Norgren<br>View a PDF of the paper titled Stateful Inference for Low-Latency Multi-Agent Tool Calling, by Victor Norgren

View PDF<br>HTML (experimental)

Abstract:Multi-agent tool calling is becoming the dominant interaction pattern for LLM-based systems, yet existing inference frameworks treat each tool call as an independent request, re-processing the entire conversation from scratch even though 85-95% of the prompt is unchanged from the previous turn.

We present a stateful inference architecture that converts the $O(n_t)$ per-turn cost of conventional serving into an $O(\Delta_t)$ delta-only cost: a persistent KV cache lives across turns and advances by ingesting only the new tokens, while a radix prefix cache extends this across interleaved multi-agent traffic and a prompt-lookup speculative decoder accelerates structured output. Against vLLM and SGLang on novel, fully-generated workloads, the reference implementation is $2.1\times$ faster per turn on a 6-turn agentic workflow and $4.2\times$ on the median turn of a 35-turn one, halving end-to-end wall time. The advantage comes from stateful reuse and speculation, not caching.

Subjects:

Machine Learning (cs.LG)

Cite as:<br>arXiv:2605.26289 [cs.LG]

(or<br>arXiv:2605.26289v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.26289

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Victor Norgren [view email]<br>[v1]<br>Mon, 25 May 2026 19:27:49 UTC (63 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Stateful Inference for Low-Latency Multi-Agent Tool Calling, by Victor Norgren<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

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

Change to browse by:

cs

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?)

IArxiv recommender toggle

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