Notes2Skills：從實驗室筆記本到具備置信度感知能力的科學智能體技能

摘要

科學發現的工作流程通常包含並高度依賴實驗筆記，研究人員在其中記錄觀察結果、解讀不確定的結果，並規劃後續實驗。這類富含資訊的實驗筆記保留了科學推理的演進過程及作者的疑慮，而非出版成果中所呈現的修飾後最終結果，為人工智慧在更全面、更深入的層面上參與科學探索提供了寶貴機會。然而，過去大多數關於科學文本的研究聚焦於論文、操作協議或結構化資料庫，忽略了非正式的實驗筆記作為科學AI代理輸入的潛力。這一缺口影響重大，因為實驗筆記往往在同一段落中混雜了已驗證的觀察、暫定的判斷及可能的實驗下一步行動。如果這些訊號被混淆，AI代理可能會將不確定的科學判斷誤認為已確認的結論或可執行的行動。為此，我們提出了Notes2Skills，一個將實驗筆記轉化為可驗證技能、同時保留作者確定性的兩階段框架。在七種條件及三次濕實驗室操作的測試中，Notes2Skills是唯一既不會將不確定的筆記誤認為明確指令、也不會捨棄明確指令的配置。我們證明了確定性保留是實驗筆記與可靠代理技能之間缺失的一環，為更安全的AI共同科學家系統開闢了一條道路。

English

Scientific discovery workflows usually contain and rely heavily on lab notes, where researchers record observations, interpret uncertain results, and plan follow-up experiments. Such informative lab notes preserve evolving scientific reasoning and author uncertainty, rather than polished final results exhibited in publications, providing a valuable opportunity for AI to engage in scientific exploration at a more comprehensive and deeper level. However, most prior work on scientific text focuses on papers, protocols, or structured databases, leaving informal laboratory notes underexplored as inputs to AI agents for science. This gap matters because lab notes often intermingle validated observations, tentative judgments, and possible experimental next steps within the same passage. If these signals are conflated, an AI agent may mistake uncertain scientific judgments for confirmed conclusions or executable actions. To this end, we present Notes2Skills, a two-stage framework for turning lab notebooks into verifiable skills for scientific AI agents while preserving the author's certainty. Across seven conditions and three wet-lab sessions, Notes2Skills is the only configuration that neither mistakes uncertain notes for firm instructions nor discards firm ones. We show that certainty preservation is the missing piece between lab notebooks and reliable agent skills, opening a path toward safer AI co-scientist systems.