超越深度与宽度：流式测试时计算中的信息-余量困境
Intelligence Under Time Constraints: Rethinking Test-Time Compute
浏览论文内容
中文总结 AI 辅助
本文提出信息-余量困境，分析流式测试时计算中证据演化与计算余量的权衡，主张选择性恢复和可信的及时响应。
中文摘要 AI 辅助
当证据以不同顺序到达时，相同的任务和计算预算可能需要不同的推理策略。早期计算有更多时间完成，但依赖于不完整或可修订的证据；等待会改善信息，同时减少计算余量。我们称此为信息-余量困境。我们将证据依赖的计算任务作为分析单元：何时启动它，什么支持其结果，以及何时可以提交该结果。预先计算仅在其收益能够承受验证、失效和恢复的成本时才有价值。这适用于基于证据的增量处理、可复用的准备以及依赖未来的推测。我们提出一个关于在演化证据下进行计算的研究议程，优先考虑在受控证据修订下的选择性恢复。评估应区分早期执行效应、相对于全输入备选方案的部署价值，以及预测策略的附加价值，同时考虑共享资源成本。目标不是最大化的预先计算，而是在声明的资源范围内提供更可信、更及时的反应。
英文摘要
Intelligence under time constraints requires deciding not only how much to compute, but when computation is worth starting. We study this problem in streaming interactions, where evidence arrives incrementally and may be revised. Early computation has more time to finish but rests on incomplete evidence; waiting improves information while shrinking computational slack. We call this the information-slack dilemma. We take the evidence-dependent computational job as the unit of analysis: when to start it, what supports its result, and when that result can be committed. Advance computation is valuable only insofar as its benefits survive the costs of verification, invalidation, and recovery. This applies to grounded incremental processing and reusable preparation as well as future-dependent speculation. We propose a research agenda on computation under evolving evidence, prioritizing selective recovery under controlled evidence revisions. Evaluation should separate earlier-execution effects, deployment value against a full-input alternative, and the added value of predictive policies, while accounting for shared-resource costs. The objective is not maximal advance computation, but more trustworthy, on-time responses within a declared resource envelope.
