[2607.01308] Cache Merging as a Convergent Replicated State for Multi-Agent Latent Reasoning

2 the approach transports and colocates latent traces but does not by itself compose them, which we characterize to motivate future work."/>

2 the approach transports and colocates latent traces but does not by itself compose them, which we characterize to motivate future work." />

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Multiagent Systems

arXiv:2607.01308 (cs)

[Submitted on 1 Jul 2026]

Title:Cache Merging as a Convergent Replicated State for Multi-Agent Latent Reasoning

Authors:Carlos Baquero, Luís Brito<br>View a PDF of the paper titled Cache Merging as a Convergent Replicated State for Multi-Agent Latent Reasoning, by Carlos Baquero and 1 other authors

View PDF<br>HTML (experimental)

Abstract:Multi-agent latent reasoning composes agents' KV-caches into one context for a final agent. Prior work (Agent Primitives) does this by concatenating caches along the sequence axis with RoPE re-encoding, which we call BagMerge. BagMerge is non-commutative, and the best input ordering is unpredictable, shifting with the regime, the latent-step budget, and the model scale. We make this exchange a convergent replicated state. First, CanonicalMerge fixes the layout by content: ordering caches by mean K-norm at a middle layer renders the merged cache byte-identical under any input permutation, verified algorithmically (arity N2 the approach transports and colocates latent traces but does not by itself compose them, which we characterize to motivate future work.

Subjects:

Multiagent Systems (cs.MA)

ACM classes:<br>I.2.7; I.2.11; C.2.4

Cite as:<br>arXiv:2607.01308 [cs.MA]

(or<br>arXiv:2607.01308v1 [cs.MA] for this version)

https://doi.org/10.48550/arXiv.2607.01308

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Carlos Baquero [view email]<br>[v1]<br>Wed, 1 Jul 2026 17:05:04 UTC (55 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Cache Merging as a Convergent Replicated State for Multi-Agent Latent Reasoning, by Carlos Baquero and 1 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.MA

next >

new<br>recent<br>| 2026-07

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?)

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?)

Major funding support from