Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and build reusable resources such as indices, scripts, or procedural guidance. Most automated adaptation methods rely on task examples, trajectories, or evaluation feedback to decide what to construct, while existing task‑agnostic approaches pre‑commit to a preparation strategy for a specific environment type. This work investigates a more open 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 as a process where a studying system explores an environment under a budget and produces artifacts for a frozen solver. We compare unaided meta‑agents, archive‑equipped meta‑agents, and 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, the studied artifacts reduce the test‑time sampling needed to reach a target score, demonstrating that reusable preparation can shift computation from repeated test‑time attempts to a pre‑task study phase.
Review