Metraipolis › archive › dc_29bec05ef22b

From AutoResearch to Continual AutoResearch: Do Agents Learn Across Tasks? — arXiv:2611.05108

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.05108
License (as archived): CC0-1.0
Archived: 2026-11-04T21:38:14.776Z
SHA-256 of the archived text: b6de0bdfb91969102ad6f59f28960e2da98d8ba0ec3241900147101338f24e60
Stable URL of this page: https://metraipolis.com/documento/dc_29bec05ef22b

How to cite

From AutoResearch to Continual AutoResearch: Do Agents Learn Across Tasks? — arXiv:2611.05108 — arXiv (en), https://arxiv.org/abs/2611.05108 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29bec05ef22b (Metraipolis archive dc_29bec05ef22b, sha256 b6de0bdfb91969102ad6f59f28960e2da98d8ba0ec3241900147101338f24e60)

BibTeX

@misc{dc29bec05ef22b,
  title = {From AutoResearch to Continual AutoResearch: Do Agents Learn Across Tasks? — arXiv:2611.05108},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05108},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29bec05ef22b; sha256 b6de0bdfb91969102ad6f59f28960e2da98d8ba0ec3241900147101338f24e60},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05108. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autoresearch has shown that agents can autonomously write code, run experiments, and iteratively improve machine learning solutions. Yet most evaluations start a new agent session from scratch for each new problem, making them costly and leaving unclear whether agents can retain and apply prior insights when adapting to new tasks. We introduce CONTINUAL AUTORESEARCH, an open-ended environment that compares persistent and reset instances of the same agent under matched task streams, data, and time budget. Continual AutoResearch covers nine task families, spanning synthetic tasks, symbolic regression, time-series forecasting, and tabular AutoML. Across five frontier agents, we measure first-solution quality, research efficiency, and final held-out performance. To distinguish insight transfer from session continuity, we run a memory ablation that vary what information agents retain from prior tasks. We show that persistent state improves research efficiency of all five agents, allowing them to find stronger solutions sooner. However, these gains do not consistently translate into better final solutions. Overall, our findings suggest that retaining experience and utilizing it effectively are distinct capabilities.

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/2611.05108 — 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 2026-11-04T21:35:49.583Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).