Metraipolis › archive › dc_91fd3161bcce

Automated Stateful Specialization for Adaptive Agent Systems — arXiv:2611.01870

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01870
License (as archived): CC0-1.0
Archived: 2026-11-03T10:19:34.907Z
SHA-256 of the archived text: 439b360f8187c0291ae7795b25a32cbd2f789ec64a68cad8302213a123cc6ee2
Stable URL of this page: https://metraipolis.com/documento/dc_91fd3161bcce

How to cite

Automated Stateful Specialization for Adaptive Agent Systems — arXiv:2611.01870 — arXiv (en), https://arxiv.org/abs/2611.01870 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_91fd3161bcce (Metraipolis archive dc_91fd3161bcce, sha256 439b360f8187c0291ae7795b25a32cbd2f789ec64a68cad8302213a123cc6ee2)

BibTeX

@misc{dc91fd3161bcce,
  title = {Automated Stateful Specialization for Adaptive Agent Systems — arXiv:2611.01870},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01870},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_91fd3161bcce; sha256 439b360f8187c0291ae7795b25a32cbd2f789ec64a68cad8302213a123cc6ee2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01870. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current automated agent design frameworks produce either static workflows that lack adaptability or per-query optimizers that prevent the accumulation of deep, agent-level task expertise. We propose a new direction that reconciles these paradigms: creating stateful teams of specialist agents that accumulate knowledge over time and can be reconfigured for novel tasks entirely without human intervention. To this end, we introduce ASpec, a framework that manages this full agent lifecycle by first autonomously discovering specialist archetypes via evolutionary search and then cultivating their expertise through experience, mirroring how human experts learn through practice and reflection. We further introduce a lightweight hierarchical control policy, "retain-then-escalate," which governs when to leverage the established agent system versus when to adapt its structure. Through comprehensive experiments, we demonstrate that this approach leads to significant performance gains on expert-level scientific benchmarks like GPQA while matching the state-of-the-art on broader domain tasks, demonstrating a promising path toward agent systems that are simultaneously expert, adaptive, and efficient. We will release the code at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.01870 — 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 2026-11-03T10:19:34.812Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).