Herbert A. Simon先生紀念5 從MIT公開下載的書： Scientific Discovery: Computational Explorations of the Creative ProcessUnavailable By Patrick W. Langley, Herbert A. Simon, Gary Bradshaw, Jan M. Zytkow 到 2026年5月18 " //今天 Google IO 活動同步發表了兩篇 Nature 論文，值得學研界朋友關注"
Scientific Discovery: Computational Explorations of the Creative ProcessUnavailable
ISBN electronic:
9780262316002
Scientific discovery is often regarded as romantic and creative—and hence unanalyzable—whereas the everyday process of verifying discoveries is sober and more suited to analysis. Yet this fascinating exploration of how scientific work proceeds argues that however sudden the moment of discovery may seem, the discovery process can be described and modeled.
Using the methods and concepts of contemporary information-processing psychology (or cognitive science) the authors develop a series of artificial-intelligence programs that can simulate the human thought processes used to discover scientific laws. The programs—BACON, DALTON, GLAUBER, and STAHL—are all largely data-driven, that is, when presented with series of chemical or physical measurements they search for uniformities and linking elements, generating and checking hypotheses and creating new concepts as they go along.
Scientific Discovery examines the nature of scientific research and reviews the arguments for and against a normative theory of discovery; describes the evolution of the BACON programs, which discover quantitative empirical laws and invent new concepts; presents programs that discover laws in qualitative and quantitative data; and ties the results together, suggesting how a combined and extended program might find research problems, invent new instruments, and invent appropriate problem representations. Numerous prominent historical examples of discoveries from physics and chemistry are used as tests for the programs and anchor the discussion concretely in the history of science.
Table of Contents
//今天 Google IO 活動同步發表了兩篇 Nature 論文，值得學研界朋友關注：
- Gottweis, J., Weng, WH., Daryin, A. et al. Accelerating scientific discovery with Co-Scientist. Nature (2026). https://doi.org/10.1038/s41586-026-10644-y
這篇發表於《自然》的論文介紹了 Google 團隊開發的 Co-Scientist。這是一個基於 Gemini 的多代理 AI 系統，由生成、反思、排名、演化、鄰近和元審查六個專業代理組成。不同於傳統工具，它能在非同步框架內透過錦標賽制的演化過程與自我對弈辯論，生成前所未有、可證實的新穎科學假說，且其假說品質隨測試時計算量的增加而持續提升，未見飽和。
Co-Scientist 在生物醫學領域展現出強大實力：在白血病藥物重定向測試中，系統建議的藥物有三種經體外實驗證實能抑制細胞存活；它甚至獨立提出 cf-PICI 擴展宿主範圍的假說，與研究組尚未發表的實驗發現完全吻合。在 15 個研究目標的專家評估中，Co-Scientist 的假說水準成功超越了 Gemini 2.0 Pro、GPT-4o、OpenAI o1/o3-mini 及 DeepSeek R1 等前沿模型。
- Aygün, E., Belyaeva, A., Comanici, G. et al. An AI system to help scientists write expert-level empirical software. Nature (2026). https://doi.org/10.1038/s41586-026-10658-6
這篇發表於《自然》的論文介紹了 Google 團隊開發的 ERA（實證研究助理）。這是一個將大型語言模型與樹狀搜索結合的代理 AI 系統，能自主生成、測試並迭代改進科學軟體，有效解決了過去需要專家花費數年勞動才能創建特定領域軟體的瓶頸。
ERA 的核心機制是透過大型語言模型改寫代碼以提升可量化指標，並利用樹狀搜索引導探索與回溯。該系統在六個科學基準測試中達到專家級水準：在單細胞 RNA 測序分析中，其生成的方法超越了公開排行榜上的既有做法；在 COVID-19 預測上，也擊敗了美國 CDC 的集成模型。研究更發現，ERA 有能力透過重組現有演算法來開創全新策略。這項突破展示了 AI 在多個高風險領域同時創建科學軟體的能力，也引發了未來如何部署與治理這類系統的深遠討論。//
