AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Weaving in the Clouds: Achieving Synergistic Collaboration among LLM Agents via Federated Learning

Jiaxing Zhao, Hongbin Xie, Yuzhen Lei, Xuan Song, Zhuoran Shi, Lianxin Li, Shuangxue liu, Haoran Zhang

ICML 2026 · Multi-agent systems and games › LLM agents · approach: LLM multi-agent collaboration and safety

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes federated learning for collaboration among LLM agents in multi-agent workflows so that agents can learn jointly without pooling distributed private data.

Problem

Multi-agent LLM systems need data distributed across organizations that cannot be centrally pooled due to privacy, IP, and compliance constraints; existing federated learning methods do not fit agent collaboration on workflow-structured tasks.

Approach

Applies federated learning to LLM agent collaboration so that expert agents synergize while data stays local; the abstract is truncated, so the specific mechanism is not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add VCLayer to FedAvg-LoRA (ablation)FedAvg-LoRA · MSCoRe Automotive (Llama3-8B)METEOR: 10.73 -> 17.93Improved
add MoE router to FedAvg-LoRA (ablation)FedAvg-LoRA · MSCoRe Automotive (Llama3-8B)METEOR: 10.73 -> 17.52Improved
add DPO alignment to FedAvg-LoRA (ablation)FedAvg-LoRA · MSCoRe Automotive (Llama3-8B)METEOR: 10.73 -> 21.04Improved
add DPO to VCLayer + Router (ablation)FedWave (w/o DPO) · MSCoRe Automotive (Llama3-8B)METEOR: 18.40 -> 24.83Improved
add VCLayer and Router on top of DPO (ablation)DPO-only model · MSCoRe Automotive (Llama3-8B)METEOR: 21.04 -> 24.83Improved
add consistency loss Lcons (ablation)FedWave · MSCoRe Automotive (Llama3-8B)METEOR: 24.28 -> 24.83Improved
add continuity loss Lcont (ablation)FedWave · MSCoRe Automotive (Llama3-8B)METEOR: 24.30 -> 24.83Improved
add positional loss Lpos (ablation)FedWave · MSCoRe Automotive (Llama3-8B)METEOR: 24.41 -> 24.83Improved
add load-balancing and entropy regularizers on the router (ablation)FedWave · MSCoRe Automotive (Llama3-8B)METEOR: 24.17 -> 24.83Improved
use FedWave instead of FedAvgFedWave · MSCoRe Automotive (Llama3-8B)METEOR: 10.73 -> 24.83Improved
use FedWave instead of FedAvgFedWave · FinQAF1: 5.58 -> 3.33Hurt
use FedWave instead of FedAvgFedWave · MuSiQueEM: 3.10 -> 7.20Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy