arXiv cs.AI· Samuel Chen, Jiaru Bai, Austin Henry Cheng, Varinia Bernales, Al\'an Aspuru-Guzik·· 4 小时前AI 评分41
可验证 pXRD:用 LLM 智能体进行爬坡式粉末 X 射线衍射结构解析
Verifiable pXRD: Hill-climbing pXRD structure determination with LLM agents
AI 导读
研究者将粉末 X 射线衍射(pXRD)晶体结构解析形式化为可验证的智能体搜索问题,并发布包含 200 个模拟单相问题的 pXRD-Bench 基准。通过智能体自适应,选定结构的恢复率从 27% 提升至 69%,重复采样和验证器引导的推理时扩展可进一步提升。在 15 个实测图谱上,演化框架还能恢复参考库中缺失结构的相。
正文 · 原文
Abstract:Autonomous crystal-structure determination from powder X-ray diffraction (pXRD) remains a key bottleneck for self-driving materials laboratories. We formulate the task of pXRD structure determination as a verifiable agentic search problem: candidate structures can be assessed during inference through forward-simulated profile agreement and during evaluation through structural matching to a known reference. To benchmark progress, we introduce pXRD-Bench, a suite of 200 simulated single-phase problems spanning in-distribution structure determination, challenging and polymorphic structures, and controlled compositional and topological distribution shifts. Agent adaptation raises selected structural recovery from 27% to 69%, with further gains from repeated sampling and verifier-guided inference-time scaling. We extend this approach to experimental multiphase pXRD through a reflexive evolution framework that learns from self-generated synthetic problems. A replaceable laboratory specification defines the sample family and measurement conditions. An evolver agent uses the known generating structures and measurement parameters to diagnose solver failures and develop persistent guidance and executable tools, which are then provided to agents on measured patterns. This supplies verifiable training experience without requiring a collection of solved experimental measurements. On 15 measured patterns from solid-state synthesis, the evolved package improves average profile agreement and transfers an analogue-substitution procedure that recovers a phase whose structure is absent from the supplied reference library. These results demonstrate how learning from verifiable synthetic experience can improve agentic characterization of experimental samples whose structures are not known in advance.
| Comments: | NeurIPS 2026 Workshop AI4Mat, spotlight (earlier version) |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.17539 [cs.AI] |
| (or arXiv:2611.17539v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17539 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Samuel Chen [view email]
[v1]
Thu, 12 Nov 2026 21:49:32 UTC (1,308 KB)
来源:arXiv cs.AI · arxiv.org