arXiv AI June 6, 2026 By Chen Huang, Yuhao Wu, Wenxuan Zhang

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 10

Decentralized Multi-Agent Systems with Shared Context

arXiv:2606. 10662v1 Announce Type: cross Abstract: Multi-agent systems (MAS) can scale large language model reasoning at test time by decomposing complex problems into parallel subtasks.

By Yuzhen Mao, Azalia Mirhoseini

llms agents

arXiv Computation and Language

4d ago

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...

By Shinan Zhang, Tao Zhang, Qihui Zhu, Mengjie Zhang, Dong Jin, Yunpeng Hou, Shuangwu Chen, Xiaobin Tan, Quan Zheng, Jian Yang

llms agents efficiency benchmarks

arXiv AI

Aug 7

Unified Agent: Managing Interactions across Devices

arXiv:2608. 05729v1 Announce Type: new Abstract: As capabilities rapidly increase, AI agents can move from running inside one app to acting across a user's devices over time.

By Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei, Xin Lin, Truong Nguyen

llms agents multimodal benchmarks

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.

By Wooseong Yang, Wei-Chieh Huang, Weizhi Zhang, Yu Wang, Philip S. Yu, Junhyun Lee

llms agents benchmarks

arXiv AI

Jun 29

LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior

arXiv:2606. 28182v1 Announce Type: cross Abstract: Embodied agents operating in decentralized and partially observable environments have attracted growing attention in recent years.

By Qinhong Zhou, Chuang Gan, Anoop Cherian

llms agents robotics fine-tuning benchmarks

arXiv Machine Learning

Jul 30

Two Calls Beat Five Agents: Evaluating Multi-Agent Pipelines Against Self-Refinement for Local Language Models

arXiv:2607. 26922v1 Announce Type: new Abstract: Multi-agent LLM pipeline systems break down the task among multiple roles for better reasoning, but are benchmarked mainly with large-scale commercial models.

By Ashish Prajapati, Om Mohite

llms agents benchmarks

One email a morning, machine-written

Related stories

Decentralized Multi-Agent Systems with Shared Context

LatCom: Cross-Agent Latent Compression for Efficient Multi-Agent Collaboration

Unified Agent: Managing Interactions across Devices

XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication

LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior

Two Calls Beat Five Agents: Evaluating Multi-Agent Pipelines Against Self-Refinement for Local Language Models