Metraipolis › archive › dc_c0e433481ace
Studying Without a Syllabus: Task-Agnostic Environment Preprocessing — arXiv:2609.10824
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10824
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:23:37.244Z
- SHA-256 of the archived text
312f28d48bc50477198b52bb12a318a89d9ebc1c7ae5513a2be739b4fe170ae5- Stable URL of this page
https://metraipolis.com/documento/dc_c0e433481ace
How to cite
Studying Without a Syllabus: Task-Agnostic Environment Preprocessing — arXiv:2609.10824 — arXiv (en), https://arxiv.org/abs/2609.10824 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c0e433481ace (Metraipolis archive dc_c0e433481ace, sha256 312f28d48bc50477198b52bb12a318a89d9ebc1c7ae5513a2be739b4fe170ae5)
BibTeX
@misc{dcc0e433481ace,
title = {Studying Without a Syllabus: Task-Agnostic Environment Preprocessing — arXiv:2609.10824},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10824},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c0e433481ace; sha256 312f28d48bc50477198b52bb12a318a89d9ebc1c7ae5513a2be739b4fe170ae5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10824. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reusable resources such as indices, scripts, or procedural guidance. Most automated adaptation methods, however, rely on task examples, trajectories, or evaluation feedback to decide what to build. Existing task-agnostic approaches avoid this supervision but commit in advance to a preparation strategy for a particular type of environment. We study a more open-ended setting: can an agent study an unfamiliar environment without a syllabus, i.e. before test time and without knowledge of the downstream task distribution, and choose how to prepare it? We formalize task-agnostic environment preprocessing, in which a studying system explores an environment under a budget and produces artifacts for a frozen solver. We compare unaided and archive-equipped meta-agents with fixed synthetic-practice and corpus-processing methods across six heterogeneous benchmarks. A meta-agent variant achieves the highest Avg@3 reward on five benchmarks, while fixed corpus processing remains best on the largest corpus benchmark. Larger study budgets do not reliably improve downstream reward. Nevertheless, studied artifacts reduce the test-time sampling needed to reach a given score, demonstrating how reusable preparation can shift computation from repeated test-time attempts to a pre-task study phase. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.10824 — 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 2026-10-16T05:17:51.954Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).