arXiv AI
LatBridge: Efficient and Stable Model Replacement in Latent-Communication Multi-Agent Systems
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 30
LatCom: Cross-Agent Latent Compression for Efficient Multi-Agent Collaboration
arXiv:2609.37017v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) increasingly use latent collaboration to avoid the information loss and repeated encoding-decoding overhead of natu...
arXiv Machine Learning
Oct 8
Task-Oriented Key-Layer KV Communication for Efficient Latent Multi-Agent Collaboration
arXiv:2610.08820v1 Announce Type: new Abstract: Large language model-based multi-agent systems improve complex problem solving through collaboration, while latent communication directly transmits mod...
arXiv Computation and Language
Oct 27
HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol
arXiv:2605.25421v2 Announce Type: replace Abstract: Communication protocol design is a central challenge in large language model-based multi-agent systems. Existing single-channel approaches face an...
Hugging Face Trending Papers
Sep 29
LatCom: Cross-Agent Latent Compression for Efficient Multi-Agent Collaboration
LLM-based multi-agent systems (MAS) increasingly use latent collaboration to avoid the information loss and repeated encoding-decoding overhead of natural-language communication. However, directly for...
arXiv AI
Aug 13
XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication
arXiv:2608. 11676v1 Announce Type: new Abstract: Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redundant reasoning patterns.
arXiv AI
Jun 6
What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
arXiv:2606. 05304v1 Announce Type: new Abstract: Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that agents pass to one another is often left as unconstrained natural language.