Metraipolis › archive › dc_2cba808aaf35

Anticipating the Consequences of Curriculum Decisions with Large Language Models — arXiv:2610.04604

Source
arXiv
Original
https://arxiv.org/abs/2610.04604
License (as archived)
CC0-1.0
Archived
2026-10-06T05:30:38.360Z
SHA-256 of the archived text
3bf0dda3d57cba13b21ad8a1ced0e791d5d98b85fe9959e7109f5be743e9af67
Stable URL of this page
https://metraipolis.com/documento/dc_2cba808aaf35

How to cite

Anticipating the Consequences of Curriculum Decisions with Large Language Models — arXiv:2610.04604 — arXiv, https://arxiv.org/abs/2610.04604 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2cba808aaf35 (Metraipolis archive dc_2cba808aaf35, sha256 3bf0dda3d57cba13b21ad8a1ced0e791d5d98b85fe9959e7109f5be743e9af67)
BibTeX
@misc{dc2cba808aaf35,
  title = {Anticipating the Consequences of Curriculum Decisions with Large Language Models — arXiv:2610.04604},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04604},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2cba808aaf35; sha256 3bf0dda3d57cba13b21ad8a1ced0e791d5d98b85fe9959e7109f5be743e9af67},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04604. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automatic curriculum learning can improve the effectiveness of reinforcement learning by selecting the training experiences presented to the agent over time. Predicting the consequences of such decisions can, however, be difficult. We analyze automatic curriculum learning as a sequential decision-making problem, highlighting a gap between the quantities that determine the value of curriculum decisions and the information captured by local learning signals commonly used to guide them. We then investigate whether Large Language Models (LLMs) can exploit richer information about the learning problem to better anticipate the consequences of curriculum decisions. We introduce a method that combines online learning-progress estimates with LLM-informed estimates of (i) the potential downstream benefits of learning on each task and (ii) whether direct training on a task is currently likely to produce progress. We evaluate the approach on a custom benchmark of 256 textual goals in Craftax under different curriculum objectives. We observe the strongest gains when optimizing for individual target tasks. When optimizing across the full task set, the benefits vary across learners with different mechanisms for cross-task transfer, ranging from modest improvements in learning speed to larger gains that persist through the end of training.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.04604 — 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 2026-10-06T05:27:05.697Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).