{
  "abstract": "Multi-agent systems are commonly improved by adding agents, expanding communication networks, introducing new capabilities, increasing memory, incorporating additional knowledge, and strengthening coordination mechanisms. Although these approaches can improve collective performance, additional components may also introduce redundancy, communication overhead, conflicting decisions, unnecessary computation, coordination complexity, and interference between learned behaviors. Consequently, improving a multi-agent system may require not only adding or strengthening components but also selectively deleting components that are unnecessary, harmful, inefficient, or incompatible with the system's objectives.\n\nThis paper proposes Deletion Learning for Multi-Agent Systems (DL-MAS), a general conceptual framework that treats deletion as an explicit operation for designing, training, optimizing, and maintaining multi-agent systems. Unlike approaches that focus exclusively on removing training data, pruning neural networks, or eliminating individual agents, DL-MAS considers a broad range of potential deletion targets, including agents, capabilities, parameters, representations, memories, communication links, interaction rules, coordination mechanisms, task assignments, behavioral policies, computational operations, objectives, and external dependencies. The framework organizes deletion into three principal lifecycle stages: pre-training deletion, in-training deletion, and post-training deletion. It further considers operational deletion during system deployment and continued adaptation.\n\nDL-MAS conceptualizes deletion as a selective, objective-dependent intervention whose value must be evaluated at the collective system level rather than inferred from the isolated properties of the removed component. A formal model is introduced to represent deletion actions, their costs, their effects on collective performance, and their interactions with retained components. The framework also develops a taxonomy of deletion targets, a general deletion procedure, evaluation criteria, research propositions, and an experimental methodology. The central proposition is that, under appropriate conditions, systematically identifying and removing unnecessary or counterproductive components can improve the efficiency, reliability, adaptability, and coordination of multi-agent systems while preserving required capabilities. DL-MAS provides a foundation for investigating deletion as a general design and optimization dimension of collective intelligence.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "name": "Jincheng Zhang",
      "orcid": "0009-0005-1860-0009"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8hf7zwzps9kra.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23464366",
  "fulltext_url": null,
  "id": "8hf7zwzps9kra",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23464366",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23464366/files/Deletion%20Learning%20for%20Multi-Agent%20Systems%20(DL-MAS).pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8hf7zwzps9kra.ris",
  "sources": [
    {
      "first_seen": "2026-11-02T12:21:51Z",
      "native_id": "23464366",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23464366"
    }
  ],
  "subjects": [],
  "title": "Deletion Learning for Multi-Agent Systems (DL-MAS): A General Framework for Enhancing Collective Intelligence Through Pre-Training, In-Training, and Post-Training Deletion",
  "title_text": "Deletion Learning for Multi-Agent Systems (DL-MAS): A General Framework for Enhancing Collective Intelligence Through Pre-Training, In-Training, and Post-Training Deletion",
  "type": "preprint",
  "updated_at": "2026-11-02T12:21:51Z",
  "url": "https://research.draconitic.com/paper/8hf7zwzps9kra",
  "venue": "Zenodo",
  "versions": []
}