Metraipolis › archive › dc_95da8d022343

Multi-Agent Learning with Cooperation-Driven Optimization Dynamics — arXiv:2609.16917

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16917
License (as archived)
CC0-1.0
Archived
2026-10-15T18:31:13.087Z
SHA-256 of the archived text
585d304a1ae37faa5d71941820cf93bae2cf27c0754a446eb3488f1e3d11c9bc
Stable URL of this page
https://metraipolis.com/documento/dc_95da8d022343

How to cite

Multi-Agent Learning with Cooperation-Driven Optimization Dynamics — arXiv:2609.16917 — arXiv (en), https://arxiv.org/abs/2609.16917 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_95da8d022343 (Metraipolis archive dc_95da8d022343, sha256 585d304a1ae37faa5d71941820cf93bae2cf27c0754a446eb3488f1e3d11c9bc)
BibTeX
@misc{dc95da8d022343,
  title = {Multi-Agent Learning with Cooperation-Driven Optimization Dynamics — arXiv:2609.16917},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16917},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_95da8d022343; sha256 585d304a1ae37faa5d71941820cf93bae2cf27c0754a446eb3488f1e3d11c9bc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16917. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multilayer Artificial Neural Networks trained via backpropagation are the basic blocks of many, more complex, classification algorithms. Their strength lies in the possibility of realizing, with arbitrary precision, any function. This result comes at the cost of the large number of involved parameters to be optimized. In this work, we propose a mechanism for cooperation, i.e., information exchange among several artificial neural networks, with the goal of reducing model complexity while maintaining performance. More precisely, we consider several "small" agents, i.e., containing fewer parameters than a reference "large" one, that during training share their predictions by incorporating this information into the loss function and thus directly influence weight updates. We consider several strategies for implementing cooperation, e.g., the voter model, majority model, and weighted average model based on an agent's confidence in its prediction. We numerically compare the accuracy of those strategies on several standard benchmarks. Our results support the claim that several small agents can outperform a single large model on a given classification task; the shared signals affect each agent's optimization algorithm by modulating both the descent direction and the step size, converging toward a global consensus. The proposed proof-of-concept significantly reduces the number of parameters to be trained while preserving comparable performance, thereby limiting computational resource usage.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.16917 — 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 2026-10-15T18:00:46.628Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).