Metraipolis › archive › dc_5d86f4b4e75a
Muffin - A Shared Memory Buffer for Asynchronous AI Agents — arXiv:2610.31355
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31355
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T20:47:41.223Z
- SHA-256 of the archived text
af48b044c9e9794af33024b2ab5c58e23fdf2ac958308f08d830c7fc60e66b40- Stable URL of this page
https://metraipolis.com/documento/dc_5d86f4b4e75a
How to cite
Muffin - A Shared Memory Buffer for Asynchronous AI Agents — arXiv:2610.31355 — arXiv (en), https://arxiv.org/abs/2610.31355 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5d86f4b4e75a (Metraipolis archive dc_5d86f4b4e75a, sha256 af48b044c9e9794af33024b2ab5c58e23fdf2ac958308f08d830c7fc60e66b40)
BibTeX
@misc{dc5d86f4b4e75a,
title = {Muffin - A Shared Memory Buffer for Asynchronous AI Agents — arXiv:2610.31355},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31355},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5d86f4b4e75a; sha256 af48b044c9e9794af33024b2ab5c58e23fdf2ac958308f08d830c7fc60e66b40},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31355. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The rise of Agentic AI systems has changed the landscape of artificial intelligence by enabling strong reasoning capabilities through specialized multi-agent interaction with structured self-reflection. However, in target-driven reasoning tasks, single- and multi-agent systems are often on par in terms of performance gains. A major challenge is that failures often arise from an ineffective exchange of critical information during inter-agent interaction and coordination. Different from existing multi-agent debate paradigms that rely on synchronous turn-taking and sharing information across different agents, we propose an inter-agent protocol based on shared Memory bUFFer INference - referred to as MUFFIN - in an asynchronous agentic framework. In the first step, an orchestrator routes queries based on their reasoning demands and delegates demanding ones to a multi-agent setting, where a shared memory buffer provides asynchronous exchange of intermediate findings while an agent's private reasoning remains local. Our experiments show that our framework Muffin outperforms established competitors, achieving the best accuracy in 17 out of 20 of our benchmark settings, and provides a better quality-cost trade-off than multi-agent debate: Muffin improves accuracy by 19.2 accuracy points while using 77.4% fewer tokens, without requiring full-trace sharing. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2610.31355 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T20:47:26.481Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).