Learning Self-Orchestration in Decentralized Agent Swarms
Learning Self-Orchestration in Decentralized Agent Swarms
市場式後訓練(MPT)透過競價,聯合學習去中心化智能體羣的行動策略與自主編排,無需中央協調智能體。MPT 在具身製作、機械人導航及深度研究任務中勝過整體式後訓練;使用相同行動策略時,學得的自主編排亦優於其他協調策略。訓練後的智能體羣能更快適應相關任務,並在推理時透過擴大羣體提升表現、減少智能體退出造成的損失;程式碼及訓練模型可供使用。
Published on Oct 15
Authors:
,
,
,
Abstract
Market-based post-training jointly learns decentralized agent policies and self-orchestration via bidding, improving coordination, scalability, and robustness across embodied and research tasks.
The capabilities of an agent swarm depend on both its individual members and how they coordinate. Yet existing multi-agent systems often train agents within fixed orchestration structures, separating the learning of individual capabilities from the organization of collective behavior. We introduce market-based post-training (MPT), a framework for jointly learning action policies and self-orchestration in decentralized agent swarms. Agents express their willingness to participate through bids, which determine who acts and how collective outcomes provide local training credit. Learning both action and bidding behavior allows individual capabilities and patterns of participation to adapt together without a central coordinating agent. We evaluate MPT on embodied crafting, robot navigation, and deep research. Results show gains over monolithic post-training and confirm that agent participation indeed evolves with learning. With the same post-trained action policies, learned self-orchestration outperforms alternative coordination strategies. Ablations show that both action and bidding benefit from learning, and that learned bids provide more effective action-training signals. Beyond the original training objectives, trained swarms adapt faster to related tasks and achieve better performance with larger populations at inference time. Larger populations also suffer smaller performance losses under agent dropout, demonstrating that learned self-orchestration supports reuse, scaling, and robustness in decentralized agent swarms. Code and trained models are available at https://github.com/Embodied-Minds-Lab/MPT.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.22322
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 8
Image-Text-to-Text • 4B • Updated about 3 hours ago • 2Xkev/mc_single
Image-Text-to-Text • Updated about 3 hours agoXkev/mc_society
Image-Text-to-Text • Updated about 3 hours agoXkev/mc_society_sft
Image-Text-to-Text • 4B • Updated about 3 hours agoXkev/mc_single_sft
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.22322 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.22322 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co