Metraipolis › archive › dc_75b94a697294

Agentic Knowledge-Model Co-Evolution via Consistency Regularization — arXiv:2610.30790

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30790
License (as archived)
CC0-1.0
Archived
2026-10-25T08:32:40.992Z
SHA-256 of the archived text
a1870728d7c9ea5560ef28b1739b7435852e35ce3c18c9863c809d4957df2e5e
Stable URL of this page
https://metraipolis.com/documento/dc_75b94a697294

How to cite

Agentic Knowledge-Model Co-Evolution via Consistency Regularization — arXiv:2610.30790 — arXiv (en), https://arxiv.org/abs/2610.30790 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75b94a697294 (Metraipolis archive dc_75b94a697294, sha256 a1870728d7c9ea5560ef28b1739b7435852e35ce3c18c9863c809d4957df2e5e)
BibTeX
@misc{dc75b94a697294,
  title = {Agentic Knowledge-Model Co-Evolution via Consistency Regularization — arXiv:2610.30790},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30790},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75b94a697294; sha256 a1870728d7c9ea5560ef28b1739b7435852e35ce3c18c9863c809d4957df2e5e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30790. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents can evolve by learning from accumulated experience. Existing approaches extract reusable external knowledge, such as skills and memories, from experience to guide subsequent task solving, with some further internalizing this knowledge through model training. However, different ways of analyzing and transforming the same experience can yield knowledge with substantially different utility, even when the resulting guidance appears reasonable. Inspired by consistency regularization, we identify consistent utility gains across different ways of analyzing the same experience, rather than relying on any single way of analyzing it. We introduce SPLICE, a framework for consistency-regularized knowledge-model co-evolution. It constructs evolution views by perturbing how the same experience is analyzed, producing different knowledge candidates. Knowledge updates are then guided by common gain, which accounts for utility gains and their consistency across views. During model evolution, self-distillation internalizes the evolved knowledge alongside reinforcement learning, using knowledge associated with consistent utility degradation as a contrastive reference. The two processes interleave, with model updates driving further knowledge evolution. Experiments across diverse domains show that SPLICE outperforms knowledge evolution and model training baselines by up to 7.1 and 4.6 points in average accuracy, while its evolved knowledge reduces output tokens per correct solution by up to 44% and transfers across model sizes and families.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.30790 — 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 2026-10-25T08:31:13.032Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).