AI News HubLIVE
原文

SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication

SCALE-COMM is a self-supervised framework that decouples communication learning from policy optimization, learning compact, stable, and policy-relevant latent messages to improve coordination in multi-agent reinforcement learning. It outperforms existing methods on benchmarks and a realistic warehouse task, offering better stability, sample efficiency, and throughput.

Article intelligence

EngineersAdvanced

Key points

  • Decouples communication learning from policy optimization to reduce interference.
  • Uses contrastive learning to enforce consistency across agents and time.
  • Outperforms existing frameworks in both standard and realistic coordination tasks.

Why it matters

This matters because decouples communication learning from policy optimization to reduce interference.

Technical impact

May affect agent architecture, tool calling, workflow automation, and product integration.

[2605.27532] SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication

[Submitted on 26 May 2026]

Title:SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication

View a PDF of the paper titled SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication, by Mahmoud Abouelyazid and 1 other authors

View PDF HTML (experimental)

Abstract:Emergent communication enables partially observant Autonomous Mobile Robots (AMRs) to coordinate effectively in decentralized multi-agent reinforcement learning (MARL) settings. However, existing approaches often struggle with unstable communication protocols, ungrounded message semantics, and interference between communication learning and policy optimization, leading to degraded coordination over time. We propose SCALE-COMM (Shared, Contrastively-Aligned Latent Embeddings for COMMunication), a self-supervised framework for learning compact, stable, and policy-relevant communication representations. SCALE-COMM decouples communication learning from policy optimization by training low-dimensional latent messages that capture task-relevant planning and traffic information, while enforcing consistency across agents and time. Across standard MARL benchmarks and a realistic warehouse coordination task, SCALE-COMM consistently outperforms existing communication frameworks in both representation quality and task performance. The learned communication space yields improved stability, sample efficiency, and throughput under policy fine-tuning, demonstrating the effectiveness of representation-driven communication for scalable multi-agent coordination.

Comments: IEEE IV 2026

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2605.27532 [cs.RO]

(or arXiv:2605.27532v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2605.27532

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mahmoud Abouelyazid [view email] [v1] Tue, 26 May 2026 18:06:19 UTC (5,898 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication, by Mahmoud Abouelyazid and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-05

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

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? | Disable MathJax (What is MathJax?)