用模拟实验反馈优化科学假说排序，提升发现效率。
MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback
- 基于领域知识构建模拟器，通过反馈动态调整假说优先级。
- 在124个假说上验证，排序趋势与真实实验高度一致。
- 适合需要高效筛选假设的实验科学领域研究者。
假说排序对自动化科学发现至关重要，尤其在成本高、通量受限的自然科学研究中。现有方法仅依赖语言模型事前推理，缺乏实验反馈。本文提出实验引导排序，根据前期测试反馈优先排序假说。由于真实实验不切实际，我们设计了一个基于领域概念的模拟器，将假说表现建模为与隐藏真实值相似度的函数，并加入噪声扰动。在124个具有实验结果的假说上验证，该模拟器的排序趋势与真实结果保持一致。尽管存在偏差，但其分布类似湿实验噪声，有助于训练更鲁棒的排序策略。我们将实验引导排序建模为序列决策问题，提出一种上下文内强化学习（ICRL）框架。基于大模型的策略将假说分解为功能单元，按机制角色聚类，并依据反馈优先重组。实验表明，该方法显著优于事前基线和强型消融模型。我们的工具包包含模拟器与ICRL框架，支持系统性研究实验引导排序，策略本身亦为有力的可行性证明。
原文摘要 · Abstract (English)
Hypothesis ranking is vital for automated scientific discovery, especially in cost-intensive, throughput-limited natural science domains. Current methods focus on pre-experiment ranking, relying solely on language model reasoning without empirical feedback. We introduce experiment-guided ranking, which prioritizes hypotheses based on feedback from prior tests. Due to the impracticality of real experiments, we propose a simulator grounded in domain-specific concepts that models hypothesis performance as a function of similarity to a hidden ground truth, perturbed by noise. Validated against 124 hypotheses with experimentally reported outcomes, the simulator approximates real results with consistent trend alignment. Although deviations exist, they mimic wet-lab noise, promoting more robust ranking strategies. We frame experiment-guided ranking as a sequential decision-making problem and propose an in-context reinforcement learning (ICRL) framework. Our LLM-based policy decomposes hypotheses into functional elements, clusters them by mechanistic roles, and prioritizes recombinations based on feedback. Experiments show our approach significantly outperforms pre-experiment baselines and strong ablations. Our toolkit, comprising the simulator and ICRL framework, enables systematic research on experiment-guided ranking, with the policy serving as a strong proof of concept.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。