[2608.12123] Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control
Skip to main content
Search arXiv
Press Enter to search · Advanced search
-->
Computer Science > Distributed, Parallel, and Cluster Computing
arXiv:2608.12123 (cs)
[Submitted on 12 Aug 2026]
Title:Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control
Authors:Josef Liyanjun Chen<br>View a PDF of the paper titled Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control, by Josef Liyanjun Chen
View PDF<br>HTML (experimental)
Abstract:LLM-agent services repeatedly execute small deterministic transitions between model and tool calls: route an outcome, update state, and emit the next effect. We ask when this control path exposes enough concurrent work for GPU execution, and what changes when a GPU-computed route decision remains on device. We formalize the ready-cohort boundary using fixed-partition share F, exact offline share P*, local upper bound U, and online achieved share A. Under zero service time, unlimited capacity, and equal relative launch deadlines, a specialized dynamic program computes P* exactly. In a stationary Poisson replay of one pinned 851-session public trace panel, the primary condition at 100,000 target active sessions, K=256, and a 50 ms launch deadline gives F=30.19%, P*=43.00%, and U=45.85%. Exact packing recovers 81.83% of the opportunity lost at fixed window boundaries. The outcome-derived route key is a conditioning proxy, not proof of executable identity. A separate mechanism study keeps a GPU-computed binary decision on device instead of returning four bytes to the host and redispatching. Across four named GPU placements, the device-resident path is faster in all 36 configurations; within-placement row-median ratios range from 1.19x to 2.39x. Across both admissible mechanisms, all 14,557,440 tested batched invocations match a separately implemented host oracle. A fixed nested device graph that removes no host decision is slower in all 60 configurations across five placements. Together, the studies establish two measurable gates for GPU agent control: deadline-feasible cohort supply and observation placement. A joined finite online runtime is required to measure A, CPU displacement, and service-level benefit.
Comments:<br>14 pages, 4 figures. Includes formal proofs, trace provenance, and a reproducibility appendix. Code and artifacts: this https URL ; processed evidence: this https URL
Subjects:
Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Operating Systems (cs.OS)
Cite as:<br>arXiv:2608.12123 [cs.DC]
(or<br>arXiv:2608.12123v1 [cs.DC] for this version)
https://doi.org/10.48550/arXiv.2608.12123
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history<br>From: Josef Liyanjun Chen [view email]<br>[v1]<br>Wed, 12 Aug 2026 14:42:15 UTC (511 KB)
Full-text links:<br>Access Paper:
View a PDF of the paper titled Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control, by Josef Liyanjun Chen<br>View PDF<br>HTML (experimental)<br>TeX Source
view license
Current browse context:
cs.DC
next >
new<br>recent<br>| 2026-08
Change to browse by:
cs<br>cs.AI<br>cs.OS
References & Citations
NASA ADS<br>Google Scholar
Semantic Scholar
export BibTeX citation<br>Loading...
BibTeX formatted citation
×
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...