• Format: All submissions must be in PDF format using the NeurIPS 2026 LaTeX style file . Please include the references and supplementary materials in the same PDF as the main paper. The maximum file size for submissions is 50MB. Submissions that violate the NeurIPS style (e.g., by decreasing margins or font sizes) or page limits may be rejected without further review. 

• Double-Blind Reviewing: The reviewing process will be double blind. As an author, you are responsible for anonymizing your submission. In particular, you should not include author names, author affiliations, or acknowledgements in your submission and you should avoid providing any other identifying information (even in the supplementary material).

  1. • Dataset & Benchmark Submissions: For submissions containing new data or benchmarks, non-anonymous external links may be included in the paper.

• Dual-Submission Policy: We welcome ongoing and unpublished work. We will also accept papers that are under review at any venue at the time of submission. Submissions under review in venues for related fields (e.g. materials science, chemistry) are welcome. Per NeurIPS guidelines, work that is concurrently published at NeurIPS or has been published at prior machine learning venues is not eligible. We will consider work that builds upon prior published work (e.g., small modifications that might not lead to a standalone paper) if we believe it can add to the discussion and knowledge sharing quality of the workshop. In such cases, authors should make clear why they are submitting the work.

• Non-Archival: The workshop is a non-archival venue and will not have official proceedings. Workshop submissions can be subsequently or concurrently submitted to other venues. 

• Visibility: Submissions and reviews will not be public. Only accepted papers across the different tracks will be made public on the workshop website.

• AI4Mat-NeurIPS 2026 Themed Track: We especially encourage papers aligned to the themed track - "Translational AI for Materials Research".

• Findings Track: We encourage the submission of diverse forms of preliminary work through the Findings Track.

Agent-based systems have become one of the fastest-growing areas of AI for materials science, and submissions describing agents for chemistry and materials research arrive in growing numbers. Given the pace of this growth, and AI4Mat's aim to provide a space for discussing intersectional research, the checklist below is intended to help workshop authors write agent papers that are useful to the AI for materials community and can be reviewed appropriately. Agent papers should be grounded in a real materials problem, explicit about what is new, transparent about the data and systems involved, and evaluated against baselines and objectives that matter scientifically. The checklist is guidance rather than a requirement, since not every item will apply to every paper, but submissions that stray far from it are more likely to be rejected.

AI4Mat-NeurIPS-2026 Agent Paper Submission Checklist

Materials Science Problem and Design

• The materials problem is clearly stated, with justification for why an agentic approach is warranted.

• The paper's novelty is stated explicitly: what is new relative to prior agent systems and prior materials methods, and which components are original versus adapted.

• Architecture is documented, including system components, tools, memory, planning strategy, APIs called, simulators or experimental equipment connected to the agent, and points of human oversight, intervention, or approval.

• Underlying models are named with versions; prompt strategies described.
  
  

Data & Workflow Integration

• The scientific content of the data is described, including but not limited to: material systems, properties, synthesis procedures and processing conditions, characterization measurements, and the underlying materials science concepts and fundamentals.

• The origin and type of the data is specified (experiment, simulation, literature) along with relevant citations.

• Coverage and limits of the data are stated: regions of chemical or process space that are well or poorly sampled, and any bias toward successful or published outcomes.

• Integration with simulation, characterization, or experimental workflows is explained as appropriate.

Evaluation & Benchmarking

• Relevant baselines are specified (non-agentic methods, prior practice, or human experts). Baselines should extend beyond simple system ablations.

• Benchmarks and metrics are clearly designed and tied to a broader scientific objective. Error metrics and standard deviations across runs are reported for relevant experiments.

Limitations, Reliability & Reproducibility

• Failure modes, limitations, open challenges, and transferable insights are discussed honestly. For agents acting on physical equipment, safety guardrails and controls are described.

• Code, configs, and prompts are released, or their absence justified.

• Compute cost, runtime, and tool call budgets are reported to the extent possible.

This year, AI4Mat is partnering with Advanced Intelligent Systems and Advanced Intelligent Discovery, two Wiley journals, for a special collection. Top-tier submissions on AI for materials design will be considered for publication in a special collection in the journal track. The submission process for the workshop will remain the same as for AI4Mat-NeurIPS-2026 with a single round of reviews through OpenReview. For the special collection in Advanced Intelligent Systems and Advanced Intelligent Discovery, manuscripts will undergo some additional steps:

• The program committee will identify high-quality manuscripts from the set of accepted contributions and recommend them for submission to the Wiley Journals' special collection.

• Authors will have the option to indicate if they would like their submission to be considered for the Wiley Journals' special collection for AI4Mat-NeurIPS-2026. Authors could also indicate their choice of journal out of Advanced Intelligent Systems and Advanced Intelligent Discovery.

  • Authors of recommended manuscripts interested in publication in Wiley Journals will have to prepare a full article, and the article types including all author guidelines can be found here. The selected authors will receive an invitation email from Wiley, with a unique link for the manuscript submission.

  • Authors should keep in mind that publication in Wiley Journals constitutes a peer-reviewed publication of the work and as such the manuscript may not be published in other venues depending on dual submission policies. This is different from regular workshop submissions which are non-archival.

  • Manuscripts submitted to the Wiley Journals' special collection will undergo peer review through Wiley in-house editorial team, in the same manner and to the same high standard as regular issue articles. Only accepted manuscripts will be included in the collection.

  • The special collection will be finalized and shared with the community in the first half 2027. 

The program committee would like to highlight some important features of the Wiley Journals' special collection:

• All accepted articles published in the Wiley Journals are fully Open Access. Your funder or institution may have an agreement with Wiley for payment of article publication charges; please visit here. Automatic waivers and discounts will be given to authors from countries on the list here.

• Articles in the special collection will be considered finished work and the manuscript will be reviewed according to that standard.

• It is possible for authors to submit a 4-page extended abstract in the first round of the workshop reviews and later extend to a full manuscript for consideration for the collection.

• Accepted articles will be published in the Wiley Journals on acceptance without being delayed by other papers in the collection.

• The program committee is open to including perspective and review articles in the collection. Both formats can be submitted through the OpenReview portal.

• Only submissions to the workshop will be considered for the special collection. It is not possible to submit manuscripts for consideration after the workshop submission deadline.

• Goals: The Translational AI for Materials Research track invites work showing how AI methods for chemistry and materials science can solve real-world problems across the materials development lifecycle, from discovery through scale-up and manufacturing. We especially seek work that moves beyond benchmarks and curated datasets to confront practical realities: messy, sparse, or heterogeneous data; integration with experimental and manufacturing workflows; and constraints of safety, cost, scalability, and manufacturability. Submissions should include experimental or field validation and/or evidence of use with an external or industrial partner, emphasizing verifiable improvements over existing methods.
  Because real-world research often involves proprietary data or performance targets, submissions that appropriately anonymize, aggregate, or mask sensitive details are welcome, provided they offer enough methodological transparency, validation, and transferable insight for meaningful scientific and community learning.
  By highlighting both successful translation and its challenges, this track aims to identify the methods, evidence, infrastructure, and best practices needed to turn advances in AI for materials into real scientific, industrial, and societal impact. Example research topics include, but are not limited to:

  • • AI-enabled materials discovery, optimization, or process development validated through physical experiments

    • Deployment of AI methods in industrial, pilot-scale, manufacturing, or other operational settings

    • Integration of AI models with experimental workflows, autonomous laboratories, process-control systems, or human decision-making

    • Approaches that incorporate safety, cost, sustainability, scalability, supply-chain, quality-control, or manufacturability constraints

    • Evidence that AI-enabled approaches improve experimental efficiency, material performance, process yield, development time, cost, or other practically relevant outcomes

    • Methods addressing reproducibility, robustness, uncertainty, and generalization across laboratories, instruments, material systems, or manufacturing environments

    • Case studies of collaboration between academic researchers, industrial partners, national laboratories, or end users

    • Critical analyses, lessons learned, and well-supported negative results from real-world deployment efforts 

• Instructions: Similar to the Paper Track, we encourage submissions of short-form papers up to 4 pages in length with unlimited pages for references and supplementary materials. We will also consider full-length papers of up to 9 pages in length for works that have been submitted or works that authors intend to submit to other venues, such as ICLR 2027 or peer-reviewed journals. Submissions should be clearly identified as short-form or full-length and we discourage works that do not fall into either category (e.g. 6 page submissions that do not meet the standards for full-length papers). We will ask reviewers to apply higher standards to full-length submissions as those are assumed to be more polished and generally complete work compared to short-form papers, which are typically regarded as work in progress.

• Goals: The goal of the Paper Track is to highlight research work related to automated materials discovery that pushes the state-of-the-art and foster discussion among workshop participants. All submissions should explain why the proposed work helps accelerate material discovery and can be related thematically to the three distinct parts of self-driving laboratories (AI-Guided Design, Automated Synthesis, Automated Characterization) in cases where the relation may be ambiguous. If a submission does not fit into one of the aforementioned thematic tracks, we encourage the authors to provide a detailed explanation of why their work relates to automated materials discovery. Example research topics include, but are not limited to:

  • AI-Guided Materials Design:

    • Machine learning algorithms and deep learning architectures for accelerated materials simulations and property modelling 

    • Generative algorithms for materials discovery based on diverse machine learning techniques (e.g. diffusion models, flow matching networks, reinforcement learning, GFlowNets)

    • Datasets, benchmarks and analysis methods

  • Automated Synthesis

    • Optimization and discovery of materials synthesis and chemical synthesis procedures 

    • Datasets, benchmarks, knowledge extraction and data processing techniques for materials synthesis

    • Machine learning algorithms for small-data regimes (e.g. active learning with costly data acquisition)

  • Automated Characterization

    • Analysis of real-world characterization data, e.g., microscopy data (including multi-modal data like images, spectra and diffraction patterns), x-ray diffraction, optimal measurements, property measurements

    • Datasets, benchmarks and automation frameworks for data collection and analysis in characterization tools amenable to machine learning algorithms

    • Machine learning algorithms in defect and anomaly detection in settings relevant to automated materials design

• Instructions: We encourage submissions of short-form papers up to 4 pages in length with unlimited pages for references and supplementary materials. We will also consider full-length papers of up to 9 pages in length for works that have been submitted or works that authors intend to submit to other venues, such as peer-reviewed conferences and journals. Submissions should be clearly identified as short-form or full-length and we discourage works that do not fall into either category (e.g. 6 page submissions that do not meet the standards for full-length papers). We will ask reviewers to apply higher standards to full-length submissions as those are assumed to be more polished and complete work compared to short-form papers, which are typically regarded as work in progress.

• Goals: The goal of the Findings & Open Challenges Track is to encourage submissions of research that has strong relevance in enabling the application of AI to automated materials design, but might not fit perfectly with the other tracks. Submissions to the findings track may include, but are not limited to:

• • Open Challenges: Submissions introducing and discussing overlooked scientific questions and potential future directions for a given application area. We encourage submissions that address open challenges and describe: 1. Why the current research and state-of-the-art fall short for a given challenges; 2. What directions the authors believe the community can focus on to help address the open challenge. We hope that submissions describing open challenges will enable the AI4Mat community to expand the range of interdisciplinary research the research community is working on.

  • Tools: Submissions introducing and discussing useful tools for research in automated materials design that can be disseminated to the research community through the workshop. Tools can be conceptual (e.g. AI for new data modalities in materials science) or practical in nature (e.g software libraries) as long as they have a clear relation to advancing the research themes of the workshop. We encourage submissions that describe novel experimental equipment, tools and workflows that can facilitate the application of machine learning to materials discovery.  

  • Behind the Scenes: Essential engineering work that can often be lost in research discussions, such as dataset preparation, putting together simulations of complex systems or assembling intricate hardware systems for different types of robotic automation workflows.

  • Surveys: Survey papers centered around a relevant theme for the workshop that provides new conclusions based on the analysis of the existing literature or highlights new insights or ideas that have received less attention.

  • Responsible Use: Submissions discussing responsible use, in an inclusive sense, of data and methods related to AI for automated materials design.

Through the findings track, we aim to learn more about and share with the community the various technical considerations and best practices needed to develop the complex systems required for state-of-the-art automated materials design.

• Instructions: We encourage submissions of short-form papers up to 5 pages in length with unlimited pages for references and supplementary materials. Submissions in this track should clearly explain how the proposed work helps accelerate material discovery in cases where the relation may be ambiguous. Reviewers will be asked to evaluate the thoroughness and quality of technical work described in the submission.