VeriPhy：面向世界模型评估与优化的智能体物理推理

摘要

生成视频的视觉流畅性并不意味着物理可靠性，且仅凭一个标量质量评分无法指出某个片段违反了哪条约束或在哪一时刻失败。我们提出 VeriPhy——一个可审计的物理验证系统。在该系统中，一个纯文本规划器在观察到任何帧之前，将提示词编译为类型化物理约束和一个经静态验证的执行计划。执行过程中，观测只会对预先声明的、指向冻结低层专家（例如分割与跟踪、计数、对所得轨迹进行十一种类型化物理测量、深度、OCR 和音频事件检测）的调用进行门控与范围限定。每项操作都会返回一条携带溯源信息的证据记录；该记录的有效载荷在可用时，要么是类型化测量结果，要么是显式标记的学习状态。类型化解析器与固定组合将可用记录映射为三值状态（支持、矛盾或未知，对外呈现为“合理”“不合理”或“弃权”），并带有完整溯源，因此每条裁决都可回溯到产生它的证据。我们的评估以包含 1,500 个片段、带有人工标注缺陷记录的语料库为锚点；这些缺陷记录从提示词指涉、空间和时间上定位了真实的生成失败。在包含 304 条此类记录、由 149 个片段构成的核心子集上，VeriPhy 检出 228 条；而在给定相同片段和相同断言的情况下，一个已发表的问题分解式评估器仅检出 164 条。仅凭召回率无法将 VeriPhy 与对同一主干模型进行整体式提示的方法区分开来——后者达到 222 条；真正的区分在于，每个决策都保留其证据记录和溯源，使得每条裁决背后的追踪过程都可一一审计，并可用作将评论者（critic）的裁决写回生成过程的接口。

English

Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of indicating the obligation a clip violates or the moment it fails. We present VeriPhy, an auditable physical-verification system in which a text-only planner compiles the prompt into typed physical obligations and a statically validated execution plan before any frame is observed. During execution, observations gate and scope only declared calls to frozen low-level experts (e.g., segmentation and tracking, counting, eleven typed physical measurements over the resulting tracks, depth, OCR, and audio-event detection). Each action returns a provenance-carrying evidence record whose payload, when usable, is either a typed measurement or an explicitly tagged learned state. Typed resolvers and fixed composition map usable records to a three-valued state (supported, contradicted, or unknown, surfaced as plausible, implausible, or abstain) with full provenance, so that every verdict is traceable to the evidence that produced it. We anchor evaluation in a 1,500-clip corpus of human-annotated flaw records that localize real generation failures in prompt reference, space, and time. On a 149-clip core carrying 304 such records, VeriPhy accounts for 228, against 164 for a published question-decomposition evaluator given the same clips and the same claims. Recall alone does not separate it from prompting the same backbone monolithically, which reaches 222; what separates them is that each decision retains its evidence record and provenance, making the traces auditable one verdict at a time and usable as the interface through which a critic verdict could be written back into generation.