Launch HN: Discovered Materials (YC P26) – 利用 AI 智能体发现新材料

Launch HN: Discovered Materials (YC P26) – 利用 AI 智能体发现新材料
Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

原始链接: https://discoveredmaterials.com/research/

该基准旨在评估人工智能模型针对特定热学、介电及力学指标，提出新型、动态稳定且与后道工序（BEOL）兼容材料的能力。模型配备了包括网络搜索、编程环境及机器学习原子间势（PET-MAD）在内的计算工具以进行筛选。候选材料必须附有经专家评审认为可行的合成方案。为确保严谨性，研究人员制定了一套基于惩罚机制的评分准则，分为“关键性”错误和“可修复”错误。合成方案由基于 GPT-5.6 的评分系统进行评估，该系统模拟专家评审；一旦出现单项关键惩罚（如物理上不可行的相选择），即判定为“不予尝试”。该框架结合了高通量材料信息学与严格的人工对齐验证，以评估大语言模型作为可靠计算材料科学家的工作能力。

Discovered Materials (YC P26) 是一家初创公司，利用人工智能代理加速半导体行业新材料的研发。随着现代 GPU 对散热需求急剧增加（例如从 700W 升至 2.3kW），散热已成为关键的工程瓶颈。现有的材料（如用于 3D 堆叠 HBM 的电介质）往往会产生热量积聚，而传统的新材料“从实验室到工厂”的开发流程通常耗时数年且需要巨额投资。创始人 Advaith 和 Akash 利用 AI 代理在数小时内计算出性能稳定的高性能材料——这些任务以往需要博士级研究人员耗时数周才能完成。尽管计算发现前景广阔，但该公司更专注于弥合模拟与实验室实证合成之间的差距。通过减少实验迭代次数，他们已经成功合成了与行业标准配方相媲美的热界面材料。该公司计划通过授权知识产权以及向半导体和化学公司出售其专有的发现工具来实现商业化。他们已经发布了初步研究成果以及材料科学领域 AI 模型的性能基准，旨在寻求行业反馈，从而完善其实现实验流程自动化的路线图。

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 $κ \geq$ $kappa, $ε_{0} \leq$ $epsilon, $Y \geq$ $youngs and $G \geq$ $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 $C_{V} (𝐪, ν)$ and group velocity $𝐯_{g} (𝐪, ν)$ of mode $ν$ and irreducible wave vector $𝐪$ with weight $w_{𝐪}$ , we approximate the thermal conductivity $κ_{e s t}$ as

$κ_{e s t} = \frac{τ}{V \sum_{𝐪} w_{𝐪}} \sum_{𝐪} \sum_{ν} w_{𝐪} C_{V} (𝐪, ν) | 𝐯_{g} (𝐪, ν) |^{2},$

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 $ε_{0}$ , 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 $ε_{\infty}$ , and one for the Born effective charges $Z^{*}$ . From these two models we can reconstruct $ε_{i o n i c}$ from the $Γ$ point optical modes (computed using the MLIP above) as

$(ε_{i o n i c})_{α β} = \frac{4 π C}{V} \sum_{ν \in o p t i c a l} \frac{{\bar{Z}}_{ν, α} {\bar{Z}}_{ν, β}}{ω_{ν}^{2}},$

where ${\bar{Z}}_{ν, β}$ are phonon eigenvector weighted Born effective charges, $4 π C$ is the mode oscillator strength and $V$ is the unit cell volume. We obtain the $ε_{0}$ tensor by adding the tensor contributions of $ε_{\infty}$ and $ε_{i o n i c}$ .

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

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).
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).
A. Hjorth Larsen et al. The atomic simulation environment — a Python library for working with atoms. Journal of Physics: Condensed Matter 29, 273002 (2017).
UK AI Security Institute. Inspect: An open-source framework for large language model evaluations. https://inspect.aisi.org.uk
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
C. Lin, J. Han, B. Xu and N. Marzari. First-principles phonon physics using the Pheasy code. arXiv:2508.01020 (2025).
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).
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).
A. Togo, L. Chaput and I. Tanaka. Distributions of phonon lifetimes in Brillouin zones. Physical Review B 91, 094306 (2015).
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
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).