Metraipolis › archive › dc_392caa39b464
AI Cosmos: An Agentic Infra for Situated Learning — arXiv:2610.40031
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40031
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:17:04.730Z
- SHA-256 of the archived text
deab6f08ea69d1b1b31fdbe719e9d6ed70f3f379e616f8c2f386e93d87d56073- Stable URL of this page
https://metraipolis.com/documento/dc_392caa39b464
How to cite
AI Cosmos: An Agentic Infra for Situated Learning — arXiv:2610.40031 — arXiv (en), https://arxiv.org/abs/2610.40031 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_392caa39b464 (Metraipolis archive dc_392caa39b464, sha256 deab6f08ea69d1b1b31fdbe719e9d6ed70f3f379e616f8c2f386e93d87d56073)
BibTeX
@misc{dc392caa39b464,
title = {AI Cosmos: An Agentic Infra for Situated Learning — arXiv:2610.40031},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40031},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_392caa39b464; sha256 deab6f08ea69d1b1b31fdbe719e9d6ed70f3f379e616f8c2f386e93d87d56073},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40031. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) can improve task performance during learning, yet these gains do not necessarily reflect learners' ability to thereafter apply the knowledge and skills independently. We present AI Cosmos, an agentic infrastructure for situated learning that organizes learning around two complementary principles: scenario-based participation and cumulative assets of practice. AI Cosmos organizes learners and role-specialized agents within learning scenarios that integrate task-relevant knowledge and, when needed, executable workbenches. An asset-memory loop preserves the processes and outcomes of practice as reusable assets with explicit provenance and dependencies. We evaluate scenario-based interaction through two preregistered randomized controlled studies examining the acquisition of legal reasoning and programming competence, holding the same underlying LLM across conditions. AI Cosmos achieves greater learning gains than a conventional LLM in legal reasoning and higher mastery of unseen programming problems than an LLM-as-Teacher baseline. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.40031 — 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 2026-10-31T06:07:23.367Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).