Metraipolis › archive › dc_26307cc19bd7

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks — arXiv:2608.03764

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03764
License (as archived)
CC0-1.0
Archived
2026-10-31T12:16:39.235Z
SHA-256 of the archived text
3e123b0f3ebddcad70003f4d218784d94e2d408cd6715bfb91553fecaa8481e8
Stable URL of this page
https://metraipolis.com/documento/dc_26307cc19bd7

How to cite

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks — arXiv:2608.03764 — arXiv (en), https://arxiv.org/abs/2608.03764 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_26307cc19bd7 (Metraipolis archive dc_26307cc19bd7, sha256 3e123b0f3ebddcad70003f4d218784d94e2d408cd6715bfb91553fecaa8481e8)
BibTeX
@misc{dc26307cc19bd7,
  title = {GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks — arXiv:2608.03764},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03764},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_26307cc19bd7; sha256 3e123b0f3ebddcad70003f4d218784d94e2d408cd6715bfb91553fecaa8481e8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03764. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks more effectively. Evaluating self-evolution is difficult: existing benchmarks provide limited coverage of economically valuable task domains, do not always design training and test tasks such that test-time gains can be attributed to training experience, and remain vulnerable to data contamination. We present GDPevo, an evolution-native benchmark grounded in GDP-related enterprise workflows, together with the fully automated data pipeline that generates it. Its core mechanism, rule hybridization, decomposes each enterprise workflow into atomic business rules, distributes subsets of these rules across training tasks, and recombines them in held-out test tasks so that test-time gains are attributable. GDPevo spans CRM, ERP, finance, healthcare, legal, and data-centric workflows. Its V1 release contains 120 tasks in 12 groups, with five training and five held-out test tasks per group. Full automation enables the pipeline to expand the suite to 240 tasks in 24 groups (V2) within two days, providing a practical response to contamination. Using GDPevo, we evaluate four agents, each comprising a harness and a model, under four supervision types. Self-evolution consistently improves held-out accuracy by up to 16.44 percentage points. But the best evolved agents remain far below the fully informed oracle ceiling of 91.6%, indicating that the self-evolution ability of current agents remains far from fully realized. We publicly release the pipeline, benchmark, and full evaluation results at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03764 — 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 2026-10-31T12:05:52.850Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).