自主研究代理已经在机器学习沙箱中展示了端到端的法学硕士自动化，其中执行提供了校准。前沿物理科学截然不同:物理推理是每种方法选择的基础,工具链通常记录不足,并且校准必须来自外部文献锚点——无支架的代理引用但不面对,来自内部先验的幻觉似是而非,无法验证的结果。我们提出了一个从 11,083 最近凝聚态物理 arXiv 论文的语料库到具有三个实质性物理发现的出版级手稿的端到端运行的管道(这里关于变磁压磁): 代理通过映射语料库自主构想一个研究方向, 通过复制已发表的参考文献来校准方法, 执行新颖的第一原理计算, 并撰写手稿 - 以文献为基础，贯穿,，跨越 47 个新上下文会话，分六个阶段仅共享磁盘状态, 和 2,162 文献咨询事件。容错源自冗余: 新环境隔离, 分布式基础, 和对抗性审查捕获任何单个会话遗漏的内容; 试点前和试点后阶段是完全自主的,，试点仅在再现失败时才需要有限的人为干预 - 操作知识管理, 不是科学方向。两种成对的故障模式——预架构基线和无飞行员消融——在校准检查点隔离结构强制的数值对抗，作为操作的接地机制。以, 为特征的失效模式, 和量化干预模式的原语, 为计算物理以外的高风险科学领域的自主研究奠定了基础。
Autonomous-research agents have demonstrated end-to-end LLM automation in machine-learning sandboxes where execution provides calibration. Frontier physical science differs categorically: physical reasoning underlies every methodology choice, toolchains are often underdocumented, and calibration must come from external literature anchors - which unscaffolded agents cite but do not confront, hallucinating plausible, unverifiable results from internal priors. We present a pipeline that runs end-to-end from a corpus of 11,083 recent condensed-matter physics arXiv papers to a publication-grade manuscript with three substantive physics findings (here on altermagnetic piezomagnetism): the agent autonomously conceives a research direction by mapping the corpus, calibrates methodology by reproducing published references, conducts novel first-principles computations, and writes the manuscript - grounded in literature throughout, across 47 fresh-context sessions in six phases sharing only on-disk state, with 2,162 literature-consultation events. Fault tolerance emerges from redundancy: fresh-context isolation, distributed grounding, and adversarial review catch what any single session misses; pre- and post-pilot stages are fully autonomous, and pilot requires bounded human intervention only at reproduction failures - operational knowledge curation, not scientific direction. Two paired failure modes - a pre-architecture baseline and a no-pilot ablation - isolate structurally enforced numerical confrontation at calibration checkpoints as the operative grounding mechanism. The primitives, characterized failure modes, and quantified intervention pattern lay a foundation for autonomous research in high-stakes scientific domains beyond computational physics.
科目: 人工智能 (cs.AI); 材料科学 (cond-mat.mtrl-sci); 计算物理学 (physicals.comp-ph)
Subjects: Artificial Intelligence (cs.AI); Materials Science (cond-mat.mtrl-sci); Computational Physics (physics.comp-ph)