[2602.13255] DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource Contention

-->

Computer Science > Artificial Intelligence

arXiv:2602.13255 (cs)

[Submitted on 2 Feb 2026 (v1), last revised 3 Jun 2026 (this version, v2)]

Title:DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource Contention

Authors:Najmul Hasan, Prashanth BusiReddyGari<br>View a PDF of the paper titled DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource Contention, by Najmul Hasan and Prashanth BusiReddyGari

View PDF<br>HTML (experimental)

Abstract:We present DPBench, a benchmark for evaluating coordination in multi-agent systems built from large language models. Existing benchmarks measure task-level success under a fixed protocol; the structural conditions under which coordination succeeds or fails at all have not been characterised. DPBench adapts the Dining Philosophers problem into a controlled testbed where the action protocol, the communication structure, and the group size each vary independently. We evaluate six agents: GPT-5.2, Claude Opus 4.5, Grok 4.1, Gemini 2.5 Flash, Llama 4 Maverick, and a uniform-random baseline. Under simultaneous action at N=5 with the default prompt, deadlock ranges from 25.0% (95% Wilson CI [11.2, 46.9]) for GPT-5.2 to 90.0% [74.4, 96.5] for Gemini 2.5 Flash; sequential action is solved by four of the six. Holding the model fixed at Gemini 2.5 Flash, three protocol variables drive deadlock from 90% to within CI of zero: three rounds of pre-commitment communication (0.0% vs. single-round 86.7%), a prompt encoding a classical concurrency primitive (0.0% for resource-ordering and symmetry-breaking, against 100% for the minimal prompt), or doubling the group from N=5 to N=10 (90.0% to 10.0%). Single-round messaging and memory of past timesteps do not change the rate at the sample size we ran. Whether the same model coordinates or deadlocks is determined by the protocol, not by the model's capability.

Comments:<br>20 pages, 4 figures

Subjects:

Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)

Cite as:<br>arXiv:2602.13255 [cs.AI]

(or<br>arXiv:2602.13255v2 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2602.13255

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Prashanth BusiReddyGari [view email]<br>[v1]<br>Mon, 2 Feb 2026 18:26:00 UTC (65 KB)

[v2]<br>Wed, 3 Jun 2026 20:03:36 UTC (184 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource Contention, by Najmul Hasan and Prashanth BusiReddyGari<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.AI

next >

new<br>recent<br>| 2026-02

Change to browse by:

cs<br>cs.MA

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?)