发表机构
Pine AI; University of Washington（松树人工智能公司; 华盛顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究测试时增加计算量的新方法，提出交互缩放概念，通过模型与外部仪器交互突破传统方法局限，在硬编码任务和视觉工件处理上展现优势，表明交互缩放真实且区别于推理和采样，需反馈和度量基于实际。
AI 中文摘要
在测试时增加计算量有两种标准方法：让模型推理更长时间或进行更多尝试并保留一个结果。但这两种方法都有隐藏限制，都是内部的。我们研究了第三种方法——交互：模型提出工件，外部仪器观察其实际行为，模型进行修正。每个循环引入真实观察，突破了前两者的上限。我们认为单个变量“基础”控制这第三轴，且在循环两侧都必须成立。在固定令牌预算的硬编码任务上，仅推理和最佳N采样都会达到平稳状态，而交互策略持续改进。在渲染视觉工件上，普通判断会忽略缺陷，而测量实际布局的工具能显示循环消除了40 - 74%的缺陷。交互缩放是真实且与推理和采样不同的，但只有当反馈和度量都基于实际时才可见。
英文摘要
There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one. Both share a hidden limit: they are internal. Every extra token comes from the same frozen weights and the same prompt, so neither can tell the model anything it does not already know. We study a third way, interaction: the model proposes an artifact, an external instrument observes how it actually behaves, and the model revises. Each cycle imports a real observation, so interaction breaks through the ceiling the other two hit. We argue that a single variable governs this third axis, grounding, and that it must hold on both sides of the loop. The feedback that drives revision must come from an instrument that actually observes the flaw, and so must the metric that scores the result. On hard coding tasks at a fixed token budget, reasoning-only and best-of-N sampling both plateau (the latter even when an oracle picks the best sample), while every interaction strategy keeps improving; our proposer-reviewer harness reaches a perfect 100% pass rate with no run-to-run variance, and the gain holds across three model families. On rendered visual artifacts, the usual judge (a vision-language model, or VLM, reading a screenshot) rates 14 of 15 visibly broken figures "perfect," because the screenshot hides the flaws before the judge can see them. A tool that measures the real layout instead shows the loop removing 40-74% of defects across four modalities; and that same VLM, used as the reviewer, makes slide layouts worse where the measuring tool repairs them. Interaction scaling is real and distinct from reasoning and sampling, but only visible when both the feedback and the metric are grounded.
