这篇论文解释了很多自动科研系统为什么卡在第一步，还给了个能算清“造工具”价值的解法 CG-Plan。
arXiv 论文提出能力门控（capability gating）概念，指出仅按信息增益/成本打分的主流实验选择策略存在结构性缺陷。当需要先构建工具、管线等能力才能获得答案时，短视规划器无法为第一步建设赋予价值。作者证明对任意前瞻深度 d，都存在实例使短视信息最大化规划器的近似比无界，甚至永远无法到达目标。论文提出增量重规划器 CG-Plan，其代价函数 h = h_cap + h_exp 显式纳入能力获取成本。在受控测试中，性能差距仅在门控条件下出现，且对每个固定深度持续存在。
Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection
Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to stop. Many systems make these decisions by maximizing a myopic score such as expected information gain per unit cost or a learned plausibility score. We identify a structural limitation of this approach. Some actions are constructive: they acquire an epistemic capability (an instrument, assay, pipeline, simulator, or abstraction) whose value lies not in the information returned immediately but in the future actions it makes available. When the least-cost route to a confident answer requires a chain of such constructions, a planner that scores actions only by information obtainable within a bounded horizon cannot value the first construction: it yields no information within the horizon and is dominated by any measurement with positive information, however small. We formulate goal-directed discovery as a stochastic shortest-path problem in belief space in which constructive experiments change the downstream action graph, and prove that for every lookahead depth d there is an instance on which every myopic information-maximizing planner has an unbounded approximation ratio, and a related instance on which it never reaches the goal. The mechanism is a capability-indistinguishability lemma: within the horizon, acquiring a capability can be observationally indistinguishable from paying for a null action. This establishes capability gating as a reachability axis of difficulty distinct from curvature (submodularity) and information order (adaptivity gaps). We introduce CG-Plan, an incremental replanner with a capability-aware cost-to-go heuristic h = h_cap + h_exp. In a controlled testbed, the performance gap appears only under gating, persists for every fixed horizon, and arises when near-miss hypotheses come from a data-consistent proposer.