AI News
商业产业 Hacker News AI 2026-08-12T07:51 正文 ok 1808 words

Launch HN：Discovered Materials（YC P26）——用 AI Agent 发现新材料

英文标题：🔶 Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

该基准测试要求模型寻找同时满足热导率、静态介电常数、杨氏模量和剪切模量指标的动态稳定新型晶体材料，并为每种候选材料提出可在 BEOL 条件下实施的薄膜合成方案。模型可使用网页搜索、Python/Bash 沙盒、材料科学软件包及基于机器学习的性质计算工具，并在最多 1 亿 token 的预算内持续探索。研究以 AI Security Institute 的 Inspect 框架评测模型，同时用人类专家评分构建合成方案审查量表，再以具备网页搜索能力的 GPT-5.6 Sol 进行评分。示例显示，即使 Claude Opus 5 提出了看似细致的六方金刚石 CVD 方案，审查器仍因缺乏可信的相选择机制而判定“不会尝试”，反映材料发现 Agent 不仅需要预测材料性质，也必须给出实验上可信、可执行的制备路径。
打开原文相关 3 · 机会 1
media3.5 KB media15.8 KB media122.7 KB

中文

最后，我们介绍用于衡量模型表现的基准测试框架、工具和评分器。所有模型的任务都是寻找满足 κ≥ $kappa、ε0≤ $epsilon、Y≥ $youngs 和 G≥ $shear 的材料。固定参数值用于界定恰当的目标区间，模型接收到的任务目标如下。

Propose dynamically stable, novel, BEOL-compatible crystalline materials that meet all of the following targets: thermal conductivity $kappa, STATIC dielectric constant $epsilon, Young's modulus $youngs, and shear modulus $shear. Every candidate must also come with a BEOL temperature and process compatible synthesis recipe that an expert review judges WOULD ATTEMPT — a candidate whose recipe is judged not worth attempting does not count. Novelty means that the material has never been deposited as a thin-film in BEOL compatible conditions in the reported literature.

我们为模型配备了一组完成该任务所需的工具。这些工具被设计为接近计算材料科学家通常可使用的工具。提供给模型的工具包括：

  • 网页搜索（使用 Exa 作为服务提供商）
  • 具备 Python 和 Bash 能力的代码沙盒，以及部分相关材料科学软件包——pymatgen¹、mp_api² 和 ASE³
  • 基于机器学习的工具，用于计算：1）动态稳定性；2）晶格热导率；3）静态介电常数；4）柔度张量

模型没有被赋予停止条件，会持续运行，直至发生错误或耗尽其总计 1 亿 token 的预算。我们使用 AI Security Institute 开源的 Inspect 框架⁴对这些模型进行基准测试。下一节将更详细讨论模型用于筛选候选材料的具体工具，随后介绍合成方案的评分流程。

提供的工具

下面列出本研究用于计算各项性质的机器学习工具。我们采用机器学习原子间势（MLIP），尤其是通用点边变换器（universal point edge transformer，UPET）基础机器学习模型 PET-MAD⁵。未来工作可使用直接密度泛函理论计算替代这些 MLIP 计算，或采取混合方法。

动态稳定性与“谐波”晶格热导率

我们使用 Pheasy⁶ 和 Phonopy⁷ 生成随机构型，并利用压缩感知方法⁸拟合二阶力常数。由此可以识别所有声子模。任何低于 −1 THz（−4.14 meV）的虚频模都被判定为动态不稳定。我们使用 PET-MAD 评估每个随机构型的能量和力。对于谐波声子计算中可获得的量，设晶胞体积为 V、比热容为 CV(𝐪,ν)、模式 ν 和具有权重 w𝐪 的不可约波矢 𝐪 的群速度为 𝐯g(𝐪,ν)，我们将热导率 κest 近似为：

κest=τV∑𝐪w𝐪∑𝐪∑νw𝐪CV(𝐪,ν)|𝐯g(𝐪,ν)|2,

其中，τ 被视为常数。该方法可有效筛除具有极平坦能带的结构，从而避免更昂贵的弛豫时间计算。

晶格热导率（LTC）

我们使用 Pheasy⁶ 和 Phonopy⁷ 生成随机构型，并采用压缩感知方法⁸拟合二阶和三阶力常数。我们在三声子散射图景下近似计算 LTC。为获得热导率，我们在弛豫时间近似下求解玻尔兹曼输运方程⁹。LTC 评估中纳入同位素效应；由于候选材料预期具有较高带隙（较低介电常数），我们忽略电子贡献。

静态介电常数

我们使用通用材料张量网络（General Materials Tensor Network，GMTNet）¹⁰获得静态介电常数 ε0，并以 JARVIS DFPT 数据库¹¹为训练数据。我们并非直接拟合静态介电常数，而是训练两个独立模型——一个用于电子／高频介电常数 ε∞，另一个用于 Born 有效电荷 Z*。基于这两个模型，我们可以利用 Γ 点光学模（由上述 MLIP 计算）重建 εionic：

(εionic)αβ=4πCV∑ν∈opticalZ¯ν,αZ¯ν,βων2,

其中，Z¯ν,β 是经声子本征矢加权的 Born 有效电荷，4πC 为模式振子强度，V 为晶胞体积。通过叠加 ε∞ 和 εionic 的张量贡献，我们得到 ε0 张量。

力学性质

我们从材料的柔度张量获得杨氏模量和剪切模量等力学性质。具体方法是对晶胞施加 12 种不同构型的应变，并再次使用 MLIP 预测与这些构型相关的应力 σ。

合成方案评分流程

我们向人类专家提供了一些由 LLM 生成的合成方案，供其独立评分。根据这些评分，我们构建了可用于评估任何候选方案的评分量表。每个量表均采用扣分格式：方案如错误说明或遗漏任何信息，就会被扣分。扣分分为两类——关键问题和可修正问题。关键问题会自动确保该方案不会被尝试。评审可根据可修正问题列表，决定是否尝试某一方案，或将其标记为不太可能成功。我们的评分器采用具备 OpenAI 网页搜索能力的 GPT-5.6 Sol，以三次评分中最差的一次为准，因为这种方式与人类反馈的相关性最高。

评分示例

Tool: 2.45 GHz microwave-plasma CVD (low-temperature, seeded).
- Substrate: 300 mm Si wafer with 100 nm PECVD SiO2; sputter a 3 nm AlN or 2 nm h-BN (0001)
  buffer to template hexagonal stacking.
- Seeding: spin-coat 5 nm detonation-nanodiamond colloid (0.1 g/L in DMSO), 60 s ultrasonic,
  N2 blow-dry; seed density >1e11 cm-2; O2-plasma descum 10 s before seeding.
- Gas: 0.4% CH4 in H2, 300 sccm total, 15 Torr; microwave power 600 W with pulsed duty cycle 30%
  to hold substrate at 380-400 °C (pyrometer + He-backside-cooled stage).
- Bias: -80 V DC pulsed substrate bias for the first 10 min (bias-enhanced nucleation), then float.
- Growth: 8 h → 80-150 nm continuous film; endpoint by in-situ laser reflectance interferometry.
- Post: 5 min H2 plasma at 350 °C for surface termination; optional 400 °C, 30 min N2 anneal.
- Phase ID: UV Raman (lonsdaleite 1315-1325 cm-1 vs cubic 1332 cm-1, no 1580 cm-1 G-band), GIXRD
  hexagonal (100)/(002)/(101) reflections absent in cubic diamond, cross-section TEM/SAED for
  ABAB stacking; graphitic/DLC contamination shown by D/G bands.

这是 Claude Opus 5 提出的六方金刚石——蓝丝黛尔石（lonsdaleite）——种子微波等离子体 CVD 方案，并依据 PECVD 量表进行评分。评分器返回结果为 不会尝试（WOULD NOT ATTEMPT）：存在一项关键问题，仅此一项就足以结束判定；此外还有五项可修正问题。

在量表的 17 项标准中，适用的扣分项包括：

  • 没有具体的工艺或选择手段能够促成目标相形成。 这是关键问题，仅凭这一项便可决定结论。
  • 如使用等离子体，其规格说明不充分——包括源、功率、气体和偏压。
  • 缺失或错误说明气体流量或沉积顺序。
  • 未说明废气处理，包括抽气、洗涤或减排措施。
  • 工艺条件虽然可能形成目标相，但条件不足。
  • 所提出的表征方法无法验证材料组分和目标相。

评分器对关键问题的表述如下：

相选择概念无法可信地产生有序的 2H P6₃/mmc 碳。纳米金刚石种子 MPCVD 会直接从种子晶粒生长，使埋置的 h-BN/AlN 缓冲层无法控制堆垛；常规爆轰种子为立方金刚石。偏压和低温退火均未提供已经证明的 ABAB 堆垛形成机制。近期获得相纯六方金刚石的方法，反而是在 20 GPa、1,300–1,900 °C 条件下使用取向石墨。

其总体总结如下：

CH₄/H₂ 等离子体和高密度纳米金刚石播种或许能够形成连续纳米晶金刚石薄膜。但它们无法为指定的有序 P6₃/mmc 相提供可信路径：生长将主要起始于立方纳米金刚石种子，从而实际上与所提议的六方缓冲层隔离。按当前描述，该 300 mm 工艺的功率也严重不足，脉冲和气体时序并不完整，并且没有废气处理方案。最后，Raman、GIXRD 和通用 SAED 可能会将存在层错或孪晶的立方金刚石误识别为六方金刚石。我不会将其作为蓝丝黛尔石制备方案进行尝试，尽管它可以被重新设计为一项立方纳米晶金刚石实验。

参考文献

  1. S. P. Ong, W. D. Richards, A. Jain, G. Hautier, M. Kocher, S. Cholia, D. Gunter, V. L. Chevrier, K. A. Persson and G. Ceder. Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis. Computational Materials Science 68 , 314–319 (2013).
  2. A. Jain, S. P. Ong, G. Hautier, W. Chen, W. D. Richards, S. Dacek, S. Cholia, D. Gunter, D. Skinner, G. Ceder and K. A. Persson. Commentary: The Materials Project: A materials genome approach to accelerating materials innovation. APL Materials 1 , 011002 (2013).
  3. A. Hjorth Larsen et al. The atomic simulation environment — a Python library for working with atoms. Journal of Physics: Condensed Matter 29 , 273002 (2017).
  4. UK AI Security Institute. Inspect: An open-source framework for large language model evaluations. https://inspect.aisi.org.uk
  5. A. Mazitov, F. Bigi, M. Kellner, P. Pegolo, D. Tisi, G. Fraux, S. Pozdnyakov, P. Loche and M. Ceriotti. PET-MAD, a lightweight universal interatomic potential for advanced materials modeling. Nature Communications 16 , 10653 (2025). arXiv:2503.14118
  6. C. Lin, J. Han, B. Xu and N. Marzari. First-principles phonon physics using the Pheasy code. arXiv:2508.01020 (2025).
  7. A. Togo and I. Tanaka. First principles phonon calculations in materials science. Scripta Materialia 108 , 1–5 (2015). See also A. Togo, First-principles phonon calculations with Phonopy and Phono3py , Journal of the Physical Society of Japan 92 , 012001 (2023).
  8. F. Zhou, W. Nielson, Y. Xia and V. Ozoliņš. Lattice anharmonicity and thermal conductivity from compressive sensing of first-principles calculations. Physical Review Letters 113 , 185501 (2014). See also Compressive sensing lattice dynamics. II. Efficient phonon calculations and long-range interactions , Physical Review B 100 , 184309 (2019).
  9. A. Togo, L. Chaput and I. Tanaka. Distributions of phonon lifetimes in Brillouin zones. Physical Review B 91 , 094306 (2015).
  10. K. Yan, A. Saxton, X. Qian, X. Qian and S. Ji. A space group symmetry informed network for O(3) equivariant crystal tensor prediction. International Conference on Machine Learning (ICML) 2024. arXiv:2406.12888
  11. K. Choudhary, G. Cheon, E. Reed and F. Tavazza. High-throughput density functional perturbation theory and machine learning predictions of infrared, piezoelectric and dielectric responses. npj Computational Materials 6 , 64 (2020).

English / 原文

Lastly, we describe the harness, tools and graders used in this benchmark to measure model performance. All models are tasked with finding materials where κ≥ $kappa, ε0≤ $epsilon, Y≥ $youngs and G≥ $shear. The pinned values are chosen to define the appropriate desired window, and the objective below is what the model is given.

  Propose dynamically stable, novel, BEOL-compatible crystalline materials that meet all of the following targets: thermal conductivity $kappa, STATIC dielectric constant $epsilon, Young's modulus $youngs, and shear modulus $shear. Every candidate must also come with a BEOL temperature and process compatible synthesis recipe that an expert review judges WOULD ATTEMPT — a candidate whose recipe is judged not worth attempting does not count. Novelty means that the material has never been deposited as a thin-film in BEOL compatible conditions in the reported literature.

We equipped the models with a set of tools to accomplish this task. These were designed to be similar to tools that would be available to a computational materials scientist. The tools we provided the model were:

  • Web search (using Exa as the provider)
  • A coding sandbox with python and bash capabilities and some relevant materials science packages — pymatgen1, mp_api2 and ASE3
  • Machine learning based tools to compute 1) the dynamic stability, 2) the lattice thermal conductivity, 3) the static dielectric constant, and 4) the compliance tensor

The model was given no stopping condition, and proceeds until it hits an error or exhausts its total token budget of 100 million tokens. We use the AI Security Institute’s open source Inspect framework4 to benchmark these models. In the next section we discuss in more detail the implemented tools used by the model to screen the proposed candidates. Then we discuss the synthesis scoring procedure.

Tools provided

Below, we list the machine learning based tools we used in this study to compute the various properties. We leverage machine learning interatomic potentials (MLIPs), in particular the universal point edge transformer (UPET) foundation machine learning model PET-MAD5. In future work direct density functional theory calculations can be incorporated in place of these MLIP calculations, or a hybrid approach can be taken.

Dynamic stability and "harmonic" lattice thermal conductivity

We use Pheasy6 and Phonopy7 to generate random configurations to fit the second order force constants using the compressed sensing method8. This allows us to identify all the phonon modes. Any imaginary modes below −1 THz (−4.14 meV) are determined to be dynamically unstable. We evaluate the energy and forces of every random configuration using PET-MAD. From quantities available from a harmonic phonon calculation in a unit cell volume V, with specific heat capacity CV(𝐪,ν) and group velocity 𝐯g(𝐪,ν) of mode ν and irreducible wave vector 𝐪 with weight w𝐪, we approximate the thermal conductivity κest as

κest=τV∑𝐪w𝐪∑𝐪∑νw𝐪CV(𝐪,ν)|𝐯g(𝐪,ν)|2,

where τ is treated as a constant. This effectively screens out structures with extremely flat bands, avoiding the more expensive relaxation time computation.

Lattice thermal conductivity (LTC)

We use Pheasy6 and Phonopy7 to generate random configurations to fit the second and third order force constants using the compressed sensing method8. We approximate the LTC in the three phonon scattering picture. To obtain the thermal conductivity we solve the Boltzmann transport equation in the relaxation time approximation9. We include isotope effects in our evaluation of LTC, and neglect the electronic contribution due to the expected high band gap (low dielectric constant) of the proposed candidates.

Static dielectric constant

We use a General Materials Tensor Network (GMTNet)10 to obtain the static dielectric constant ε0, by fitting to the JARVIS DFPT database11. Instead of fitting the static dielectric constant directly, we train two separate models — one for the electronic/high frequency dielectric constant ε∞, and one for the Born effective charges Z*. From these two models we can reconstruct εionic from the Γ point optical modes (computed using the MLIP above) as

(εionic)αβ=4πCV∑ν∈opticalZ¯ν,αZ¯ν,βων2,

where Z¯ν,β are phonon eigenvector weighted Born effective charges, 4πC is the mode oscillator strength and V is the unit cell volume. We obtain the ε0 tensor by adding the tensor contributions of ε∞ and εionic.

Mechanical properties

We obtain the mechanical properties of Young’s and shear modulus from the compliance tensor of the material. This is evaluated by straining the unit cell in 12 different configurations and predicting the stresses σ associated with those configurations, using the MLIP once again.

Synthesis grading procedure

We provided some LLM generated recipes to human experts to grade independently. From these gradings we built rubrics to grade any proposed recipe. Each rubric is a penalty based format, where the recipe is deducted for incorrectly specifying or omitting any information. There are two types of penalties — critical and fixable. A critical penalty automatically guarantees the recipe would not be attempted. A judge is allowed to decide from the list of fixable penalties whether to attempt a recipe or mark it as unlikely to succeed. For our grader we use a worst of three GPT-5.6 Sol with OpenAI’s web search capabilities, as it correlated best with human feedback.

Example Grading

Tool: 2.45 GHz microwave-plasma CVD (low-temperature, seeded).
- Substrate: 300 mm Si wafer with 100 nm PECVD SiO2; sputter a 3 nm AlN or 2 nm h-BN (0001)
  buffer to template hexagonal stacking.
- Seeding: spin-coat 5 nm detonation-nanodiamond colloid (0.1 g/L in DMSO), 60 s ultrasonic,
  N2 blow-dry; seed density >1e11 cm-2; O2-plasma descum 10 s before seeding.
- Gas: 0.4% CH4 in H2, 300 sccm total, 15 Torr; microwave power 600 W with pulsed duty cycle 30%
  to hold substrate at 380-400 °C (pyrometer + He-backside-cooled stage).
- Bias: -80 V DC pulsed substrate bias for the first 10 min (bias-enhanced nucleation), then float.
- Growth: 8 h → 80-150 nm continuous film; endpoint by in-situ laser reflectance interferometry.
- Post: 5 min H2 plasma at 350 °C for surface termination; optional 400 °C, 30 min N2 anneal.
- Phase ID: UV Raman (lonsdaleite 1315-1325 cm-1 vs cubic 1332 cm-1, no 1580 cm-1 G-band), GIXRD
  hexagonal (100)/(002)/(101) reflections absent in cubic diamond, cross-section TEM/SAED for
  ABAB stacking; graphitic/DLC contamination shown by D/G bands.

This is Claude Opus 5 proposing hexagonal diamond — lonsdaleite — by seeded microwave-plasma CVD, graded against the PECVD rubric. The grader returned WOULD NOT ATTEMPT : one critical penalty, which ends the judgement on its own, alongside five fixable ones.

The penalties applied, of the rubric’s 17 criteria:

  • There is no specific processing or choices leading to some desired phase formation. This is the critical one, and it decides the verdict on its own.
  • If a plasma is used it is not well specified — source, power, gases, bias.
  • Gas-flow or deposition sequence is missing or misspecified.
  • Exhaust handling, including pumping and scrubbing or abatement, is not specified.
  • The processing conditions can form the desired phase, but they are inadequate.
  • Proposed characterization cannot validate the composition and proposed phase.

The critical penalty, in the grader’s words:

The phase-selection concept does not credibly produce ordered 2H P6₃/mmc carbon. Nanodiamond-seeded MPCVD grows directly from the seed crystallites, screening the buried h-BN/AlN buffer from controlling stacking; conventional detonation seeds are cubic diamond. Neither the bias nor low-temperature anneal provides a demonstrated ABAB-stacking mechanism. Recent phase-pure hexagonal diamond instead used oriented graphite at 20 GPa and 1,300–1,900 °C.

and its overall summary:

The CH₄/H₂ plasma and dense nanodiamond seeding could plausibly produce a continuous nanocrystalline diamond film. They do not, however, provide a credible pathway to the specified ordered P6₃/mmc phase: growth will originate on predominantly cubic nanodiamond seeds, effectively isolating it from the proposed hexagonal buffer. The 300 mm process is also severely underpowered as written, with incomplete pulse and gas sequencing and no exhaust plan. Finally, Raman, GIXRD, and generic SAED could misidentify faulted or twinned cubic diamond as hexagonal. I would not attempt this as a lonsdaleite recipe, although it could be reworked into a cubic-NCD experiment.

References

  1. S. P. Ong, W. D. Richards, A. Jain, G. Hautier, M. Kocher, S. Cholia, D. Gunter, V. L. Chevrier, K. A. Persson and G. Ceder. Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis. Computational Materials Science 68 , 314–319 (2013).
  2. A. Jain, S. P. Ong, G. Hautier, W. Chen, W. D. Richards, S. Dacek, S. Cholia, D. Gunter, D. Skinner, G. Ceder and K. A. Persson. Commentary: The Materials Project: A materials genome approach to accelerating materials innovation. APL Materials 1 , 011002 (2013).
  3. A. Hjorth Larsen et al. The atomic simulation environment — a Python library for working with atoms. Journal of Physics: Condensed Matter 29 , 273002 (2017).
  4. UK AI Security Institute. Inspect: An open-source framework for large language model evaluations. https://inspect.aisi.org.uk
  5. A. Mazitov, F. Bigi, M. Kellner, P. Pegolo, D. Tisi, G. Fraux, S. Pozdnyakov, P. Loche and M. Ceriotti. PET-MAD, a lightweight universal interatomic potential for advanced materials modeling. Nature Communications 16 , 10653 (2025). arXiv:2503.14118
  6. C. Lin, J. Han, B. Xu and N. Marzari. First-principles phonon physics using the Pheasy code. arXiv:2508.01020 (2025).
  7. A. Togo and I. Tanaka. First principles phonon calculations in materials science. Scripta Materialia 108 , 1–5 (2015). See also A. Togo, First-principles phonon calculations with Phonopy and Phono3py , Journal of the Physical Society of Japan 92 , 012001 (2023).
  8. F. Zhou, W. Nielson, Y. Xia and V. Ozoliņš. Lattice anharmonicity and thermal conductivity from compressive sensing of first-principles calculations. Physical Review Letters 113 , 185501 (2014). See also Compressive sensing lattice dynamics. II. Efficient phonon calculations and long-range interactions , Physical Review B 100 , 184309 (2019).
  9. A. Togo, L. Chaput and I. Tanaka. Distributions of phonon lifetimes in Brillouin zones. Physical Review B 91 , 094306 (2015).
  10. K. Yan, A. Saxton, X. Qian, X. Qian and S. Ji. A space group symmetry informed network for O(3) equivariant crystal tensor prediction. International Conference on Machine Learning (ICML) 2024. arXiv:2406.12888
  11. K. Choudhary, G. Cheon, E. Reed and F. Tavazza. High-throughput density functional perturbation theory and machine learning predictions of infrared, piezoelectric and dielectric responses. npj Computational Materials 6 , 64 (2020).