# Xcientist：外部化AI科学家研究合成与验证的研究框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-17 08:00
- AIHOT 分数：45
- AIHOT 链接：https://aihot.virxact.com/items/cmqiwbe8g04vvsl5wxyimgyed
- 原文链接：https://arxiv.org/abs/2606.18874

## AI 摘要

Xcientist 是一个研究框架，将文献证据、想法状态、实施计划、消融记录和修复轨迹作为持久研究工件外部化，使生成机制可落地、测试和修订。它识别出“声称漂移”——可执行工件不再支持原声称机制——作为自动化研究的失败模式。在无训练记忆系统、图结构交通预测和多尺度物理信息神经网络三项任务上，Xcientist 保留了从问题定义到机制设计、验证和有限修订的可追溯轨迹。研究主张，AI科学家评估应关注合成与验证过程是否可归因、可检查且符合科学问责。

## 正文

AI systems can increasingly automate scientific workflows, but the reasoning that links prior evidence, generated ideas, experiments and final claims often remains implicit inside model inference. Here we introduce Xcientist, a research harness that externalizes research synthesis and experimental validation into inspectable, contract-governed processes. Xcientist organizes literature evidence, idea states, implementation plans, ablation records and repair traces as persistent research artifacts, so that generated mechanisms can be grounded, executed, tested and revised without losing their evidential basis. We identify claim drift as a failure mode of automated research, where runnable artifacts no longer support the mechanism originally claimed. Across training-free memory systems, graph-structured traffic forecasting and multi-scale physics-informed neural networks, Xcientist preserves traceable trajectories from problem formulation to mechanism design, validation and bounded revision. These results suggest that AI scientists should be evaluated not only by their final artifacts, but by whether their synthesis and validation processes remain attributable, inspectable and scientifically accountable.