There is a newer version of the record available.

Published January 1, 2026 | Version v2
Preprint Open

Streamlined Interagent Protocol (Slipstream): Semantic Quantization for Efficient Multi-Agent Coordination

Description

As multi-agent LLM systems scale, coordination bandwidth becomes a primary cost driver. This paper introduces Slipstream, a protocol that performs semantic quantization: mapping free-form messages onto a shared Universal Concept Reference (UCR) and transmitting compact mnemonic anchors. Results show 82% token reduction (41.9 → 7.4 tokens average) while maintaining semantic fidelity.

Reference implementation available: pip install slipcore

Files

a2a_slipstream_extension.md

Files (343.7 kB)

Name Size Download all
md5:e09b9a718a0c25939bbeea331843fedd
9.4 kB Download
md5:93660a249810683c021aff965c8af15a
5.9 kB Preview Download
md5:2ed80a2426d951c07d3938ab8744c477
1.5 kB Preview Download
md5:949e8cb3e95a21cac64f0e7f4c0812d5
1.5 kB Download
md5:fd96386278423be5e61dc50396085c29
307.5 kB Preview Download
md5:ca420feb1e5fe043af039dfebdd780f6
16.9 kB Download
md5:f48d85ddb1a9918092846a0064834c1e
990 Bytes Download

Additional details

Related works

Is supplemented by
Software: 10.5281/zenodo.18063537 (DOI)
Software: https://github.com/anthony-maio/slipcore (URL)

Software

Repository URL
https://www.github.com/anthony-maio/slipcore
Programming language
Python
Development Status
Active

References

  • Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. EMNLP-IJCNLP 2019
  • Lloyd, S. (1982). Least squares quantization in PCM. IEEE Transactions on Information Theory
  • Sculley, D. (2010). Web-scale k-means clustering. WWW 2010
  • Linux Foundation. (2025). Agentic AI Foundation Announcement
  • Anthropic. (2024). Model Context Protocol Specification