Studying Without a Syllabus: Task-Agnostic Environment Preprocessing

The paper investigates whether a language‑model agent can autonomously study an unfamiliar environment without prior task instructions or examples, and decide how to prepare for future tasks. It formalizes task‑agnostic environment preprocessing, where a studying system explores under a budget to produce reusable artifacts for a later solver. Experiments on six diverse benchmarks show that a meta‑agent variant often outperforms fixed methods, though larger budgets do not consistently boost downstream reward, yet the artifacts still reduce test‑time sampling needed to achieve a target score.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• llms
• agents
• benchmarks