AI 记不清自己查过什么，才是它答错的主因
多模态 AI 答错题，大家总怪它看/听/读得不够准；这篇把锅甩给了「记性」:它把视频、网页、音频的观察全堆在对话历史里，越查越乱，后面的决策被前面的噪音带偏。作者做了个对照实验：只换掉规划模块，性能掉得远比换掉感知模块狠——问题不在眼睛，在脑子。解法是把「对话流水账」换成一张证据台账：哪些还没查到、哪些已确认、哪些互相矛盾，每条观察先过一道批评者过滤，只把有用的记上账。结果在 OmniGAIA 上准确率 81.4%，单题成本只有 Gemini-3.1-Pro 的四成左右。它不是你明天能装进产品的现成零件，但给了一个明确信号：下一代多模态智能体，拼的是怎么记账，不是怎么感知。
📄 原文摘要(英文)
Omni-modal agents must seek evidence across video, audio, web pages, and computation to answer questions. Their main bottleneck is planning: noisy multimodal observations accumulate in conversation history and disrupt later decisions, while multimodal models have limited capacity for multi-step planning. Controlled backend replacements support this diagnosis: replacing the planner causes a much larger performance loss than replacing the perception backend. We present Omni-Decision, an omni-modal agent built on evidence-ledger planning: it replaces the growing dialogue history with an explicit evidence ledger that records what evidence is still missing, what has been confirmed, and where records conflict. A critic reads each noisy observation and passes only the usable content to the ledger, discarding the rest, so the planner works from a compact context throughout the task. Each run records the state, action, and verdict at every step, and supervised fine-tuning and decision-level reinforcement learning on these trajectories further improve the planner. Omni-Decision achieves state-of-the-art accuracy of 81.4% on OmniGAIA at approximately 43% of Gemini-3.1-Pro's cost per question, and 65.0% on WorldSense long-video understanding, level with the strongest end-to-end model.