@inproceedings{kang-etal-2026-collaborative,
title = "Collaborative {OS} of Multi-Agent Systems",
author = "Kang, Jiazheng and
Zhao, Ruochen and
Lin, Dongying and
Li, Gezi and
Bai, Ting",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1716/",
pages = "36661--36674",
ISBN = "979-8-89176-462-0",
abstract = "Large language model-driven Multi-Agent Systems (MAS) face two key challenges in long-horizon tasks: collaboration workflows struggle to adapt to dynamic task states, and accumulated inter-agent interactions lead to lengthy, noisy contexts that degrade model performance and efficiency. To address these challenges, we propose MAS-OS, a collaborative Operating System (OS) for MAS. MAS-OS consists of three core modules: Memory Manager, Agent Scheduler, and Context Allocator. The Memory Manager maintains a structured memory pool and a global summary of agents' interaction history. Based on the evolving memory states, the Agent Scheduler selects the next active agent, while the Context Allocator provides task-relevant memories to support effective context utilization. Experiments on four benchmark datasets demonstrate the effectiveness of MAS-OS. Compared with SOTA baselines, MAS-OS achieves an average improvement of 17.42{\%} under the Llama-3.1-8B backbone. The code is available at https://anonymous.4open.science/r/MAS-OS-AD34."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2026-collaborative">
<titleInfo>
<title>Collaborative OS of Multi-Agent Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiazheng</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruochen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongying</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gezi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large language model-driven Multi-Agent Systems (MAS) face two key challenges in long-horizon tasks: collaboration workflows struggle to adapt to dynamic task states, and accumulated inter-agent interactions lead to lengthy, noisy contexts that degrade model performance and efficiency. To address these challenges, we propose MAS-OS, a collaborative Operating System (OS) for MAS. MAS-OS consists of three core modules: Memory Manager, Agent Scheduler, and Context Allocator. The Memory Manager maintains a structured memory pool and a global summary of agents’ interaction history. Based on the evolving memory states, the Agent Scheduler selects the next active agent, while the Context Allocator provides task-relevant memories to support effective context utilization. Experiments on four benchmark datasets demonstrate the effectiveness of MAS-OS. Compared with SOTA baselines, MAS-OS achieves an average improvement of 17.42% under the Llama-3.1-8B backbone. The code is available at https://anonymous.4open.science/r/MAS-OS-AD34.</abstract>
<identifier type="citekey">kang-etal-2026-collaborative</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1716/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>36661</start>
<end>36674</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collaborative OS of Multi-Agent Systems
%A Kang, Jiazheng
%A Zhao, Ruochen
%A Lin, Dongying
%A Li, Gezi
%A Bai, Ting
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F kang-etal-2026-collaborative
%X Large language model-driven Multi-Agent Systems (MAS) face two key challenges in long-horizon tasks: collaboration workflows struggle to adapt to dynamic task states, and accumulated inter-agent interactions lead to lengthy, noisy contexts that degrade model performance and efficiency. To address these challenges, we propose MAS-OS, a collaborative Operating System (OS) for MAS. MAS-OS consists of three core modules: Memory Manager, Agent Scheduler, and Context Allocator. The Memory Manager maintains a structured memory pool and a global summary of agents’ interaction history. Based on the evolving memory states, the Agent Scheduler selects the next active agent, while the Context Allocator provides task-relevant memories to support effective context utilization. Experiments on four benchmark datasets demonstrate the effectiveness of MAS-OS. Compared with SOTA baselines, MAS-OS achieves an average improvement of 17.42% under the Llama-3.1-8B backbone. The code is available at https://anonymous.4open.science/r/MAS-OS-AD34.
%U https://aclanthology.org/2026.findings-emnlp.1716/
%P 36661-36674
Markdown (Informal)
[Collaborative OS of Multi-Agent Systems](https://aclanthology.org/2026.findings-emnlp.1716/) (Kang et al., Findings 2026)
ACL
- Jiazheng Kang, Ruochen Zhao, Dongying Lin, Gezi Li, and Ting Bai. 2026. Collaborative OS of Multi-Agent Systems. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 36661–36674, Budapest, Hungary. Association for Computational Linguistics.