Towards Agentic AI for Science: Hypothesis Generation, Comprehension, Quantification, and Validation (ACM Web Conference, 2025)
April 28-29, 2025 | Sydney, Australia
About the Workshop
Our mission is to foster interdisciplinary collaboration to develop fully autonomous AI systems, addressing challenges like benchmark datasets, human-AI collaboration, robust tools and methods for validating AI outputs, and trustworthiness. By tackling these issues, we can unlock AI's transformative potential in research. In this workshop, themed Agentic AI for Science, we will explore these critical topics and welcome diverse perspectives. We will focus on integrating agentic AI systems to enhance scientific discovery while upholding rigorous standards. For AI to contribute effectively, it must generate novel hypotheses, comprehend their applications, quantify testing resources, and validate feasibility through well-designed experiments. This workshop serves as a vital forum for collaboration and knowledge-sharing aimed at redefining the landscape of scientific discovery. This workshop aims to address four main research thrusts to propel future research, including (non-exclusively):
Thrust 1. Design and development of agentic AI systems for scientific discovery. The emergence of agentic AI, powered by foundation models—particularly generative models—opens up unprecedented opportunities for scientific discovery. These systems can potentially revolutionize various aspects of the scientific process, including hypothesis generation, comprehension of complex scientific phenomena, quantification, and validation. Designing and developing effective agentic AI systems for scientific discovery is both exciting and non-trivial. Pioneering work in this field has already demonstrated the promise of leveraging scientific tools, agents, and knowledge graphs. Notable examples include ChemCrow, which showcases the potential of AI in chemistry; Crispr-GPT, which applies AI to genetic engineering; and SciAgents , which illustrates the power of multi-agent systems in scientific discovery. These groundbreaking studies highlight the transformative potential of agentic AI in accelerating scientific progress and opening new avenues for research. Key research topics in this thrust include (but not limited to):
- Developing scientific foundation models: Tailoring general foundation models specifically for various scientific fields to enhance relevance and accuracy.
- Effective scientific tool augmentation: Enhancing existing scientific tools and methodologies with agentic AI capabilities.
- Multi-agent decomposition design: Developing frameworks for scientific hypothesis generation using multiple specialized AI agents.
- Human-in-the-loop agentic systems: Improving reliability and interpretability of AI-driven scientific discoveries through strategic human intervention.
Thrust 2. Theoretical foundation for scientific agentic AI. Developing agentic scientific AI requires methods to quantify the predictions and performance of these systems, as well as to validate the scientific hypotheses they generate. A thorough investigation of agentic scientific AI systems also demands solid theoretical foundations and tools to ensure guarantees on their behavior. To analyze and evaluate such systems, we will incorporate theoretical tools in modeling, logical reasoning, model validation and diagnosis, interpretable AI, and other general methods that can provide guarantees on agentic systems. Key topics in this area include, but are not limited to, the following:
- Theoretical foundation: Statistical models and theories of agentic scientific AI, such as theoretical studies on in-context learning, multi-agent communications, game theory, physics-informed hard and soft optimization constraints, and neural operators.
- Logic reasoning: Inductive, deductive, and abductive reasoning; Bayesian reasoning and probabilistic programming; neural-symbolic approaches.
- Model quantification, validation, diagnosis: Theory-driven metrics for quantifying AI system performance; self-evaluation of LLMs; data valuation and data-centric AI; diagnostics for data, architecture, and training processes; creation of standardized benchmarks for evaluating the validity of scientific hypothesis generation; scientific facts and hallucination.
- Interpretable AI: Approaches for explaining agentic AI system behaviors; quantifying trust, safety, and transparency; mechanistic interpretability.
Thrust 3. Practical application of scientific agentic AI. Deploying agentic AI systems in practical scientific research across diverse domains presents numerous challenges, particularly due to the need for domain-specific adaptation such as the unique data formats and model constraints of each scientific field. Bias in training data poses a significant risk, especially in sensitive domains like medicine. Trustworthiness and explainability are essential for scientists to confidently integrate AI-generated hypotheses and solutions into their research. Furthermore, ethical considerations arise when AI systems potentially automate research decisions that may impact public health, policy, or environmental outcomes, underscoring the importance of responsible AI deployment in science.
- Domain-specific model adaptation: Adapting agentic AI models to handle domain-specific data formats, workflows, and tools across various scientific fields; transfer learning and data-efficient fine-tuning.
- Bias detection and mitigation: Identifying and mitigating bias in training data, model design and outputs; fairness-aware AI systems for sensitive domains like healthcare and social science.
- Robustness, trustworthiness and explainability: Methods for improving the transparency and explainability of agentic AI systems in scientific research; uncertainty interpretation and quantification.
- Ethical considerations and responsible use of agentic AI in sensitive research areas; development of AI governance models to ensure accountability and human oversight in automated scientific workflows.
Thrust 4. Open problems and challenges on scientific agentic AI. Despite the promising potential of agentic AI in scientific discovery, many open problems and challenges remain to be addressed. These may include:
- Automatic curation of domain-specific scientific domains and integration of the knowledge into agentic AI systems.
- Advanced mechanisms of multi-agent collaboration in scientific discovery, with considerations of their scalability and computational efficiency.
- Continual evolution and learning of agentic AI systems; Mechanisms for updating models and improving performance based on experimental results, new data and discoveries.
- Validation and reproducibility of results generated by agentic AI systems.
Keynote Speakers
We are honored to have invited four distinguished keynote speakers.
Dr. Michael W. Mahoney
Department of Statistics, University of California, Berkeley
Dr. Sanmi Koyejo (Tentative)
Department of Computer Science, Stanford University
Dr. Su-In Lee (Tentative)
Department of Computer Science, University of Washington
Dr. Marinka Zitnik (Tentative)
Department of Biomedical Informatics, Harvard Medical School
Dr. Markus J. Buehler
Department of Civil and Environmental Engineering, Massachusetts Institute of Technology
Call for Papers
We are pleased to announce the Workshop on Agentic AI for Science: Hypothesis Generation, Comprehension, Quantification, and Validation at The Web Conference 2025, to be held in Sydney, Australia, on April 28-29, 2025. This workshop aims to explore the transformative potential of agentic AI in scientific discovery, focusing on hypothesis generation, validation, and other critical stages of the scientific process. By fostering interdisciplinary collaboration, the workshop seeks to address challenges and unlock new opportunities in the design and application of agentic AI systems.
Workshop Themes
We invite contributions addressing the following research thrusts:
- Design and Development of Agentic AI Systems: Exploring frameworks, tools, and human-in-the-loop systems for scientific discovery.
- Theoretical Foundations: Developing statistical models and reasoning approaches for hypothesis validation and performance assessment.
- Practical Applications: Examining domain-specific adaptations, ethical considerations, and governance frameworks for responsible deployment.
- Open Problems and Challenges: Addressing issues in knowledge integration, validation, and continual improvement of agentic AI systems.
Key Focus Areas
Submissions are encouraged in the following areas (not exhaustive):
- AI-driven hypothesis generation and validation.
- Statistical and logical reasoning approaches.
- Applications of AI in scientific experimentation.
- Ethical, reproducibility, and governance challenges in AI-driven science.
Types of Contributions
Our proposed workshop invites a diverse array of paper types, including original research, position papers, and survey articles, all aimed at advancing Agentic AI research for scientific discovery.
- Original research papers: Present groundbreaking findings, innovative methodologies, or theoretical insights.
- Position papers: Provide thought-provoking perspectives on emerging trends and challenges in the field.
- Survey articles: Offer comprehensive overviews of specific topics, illuminating current research landscapes and proposing future directions.
- Published Conference/Journal Papers: Relevant papers published in top conferences/journals in recent years. The papers can be submitted as is, without following the paper format/page limit of this workshop.
Future Dates and Deadlines
- Submission Deadline (For direct submissions): January 20, 2025 (Anywhere on Earth, AoE)
- Submission Deadline (For WebConf fasttrack submissions): January 26, 2025 (Anywhere on Earth, AoE)
- Notification of Acceptance: January 27, 2025
- Camera-Ready Submission: February 07, 2025
- Workshop Dates: April 28-29, 2025
Submission Site
We will use Microsoft Conference Management Toolkit (CMT) to manage the submissions and reviewing process. All listed authors must have an up-to-date CMT profile, properly attributed with current and past institutional affiliation, homepage, Google Scholar, DBLP, ORCID, LinkedIn, Semantic Scholar (wherever applicable). The CMT profile will be used to handle conflict of interest and paper matching. Submissions will not be made public on CMT during the reviewing period.
Abstracts and papers can be submitted through the Microsoft CMT platform: Microsoft CMT Submission Site .
Acknowledgement
The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft, and they bore all expenses, including costs for Azure cloud services as well as for software development and support.
Submission Guidelines
Submissions must adhere to the ACM SIGCONF format and be submitted as PDFs. Accepted papers will be included in the conference proceedings published in the ACM Digital Library.
- Deadlines: Submission deadlines are strict, and no extensions will be granted. Placeholder/dummy abstracts are forbidden.
- Authorship: Authors must comply with the ACM authorship policy. Large Language Models (LLMs) cannot be considered authors. All authors must have contributed substantially to the work and be accountable for the entire content.
- Anonymity: Submissions must follow a double-blind review process, omitting all identifying information.
-
Formatting: Submissions must be in English, double-column format, and adhere to the ACM template. The ACM template is available at
this link.
Overleaf users can access the template
here.
Word users may use the Word Interim Template, and the recommended setting for LaTeX is:
\documentclass[sigconf, anonymous, review]{acmart}.Papers are limited to 8 pages, with unlimited pages for references and an optional appendix. The first 8 pages should be self-contained, as reviewers are not required to read past that. - Originality: For original research papers, submissions must present original work. Submissions previously presented orally, as posters, or in non-archival venues without formal proceedings (e.g., workshops or PhD symposia) are allowed. Authors may submit anonymized preprints (e.g., on arXiv or SSRN) without citing them. The ACM’s policies on plagiarism, misrepresentation, and falsification apply to all submissions. For more details, visit the ACM Plagiarism Overview.
- Ethical Use of Data and Informed Consent: Authors are encouraged to include a section on the ethical use of data and/or informed consent of research subjects, where appropriate. Submissions must comply with all ACM Publications Policies, including the Policy on Research Involving Human Participants and Subjects. Familiarize yourself with all ACM publication policies here.
WebConf fasttrack submissions
- Authors should include an Appendix following the references section, where they must directly paste the reviews received during the main review process. These reviews will be utilized to determine acceptance into the workshop. Modifying or altering reviewer comments is strictly prohibited.
- In the appendix, authors are required to include a section titled "Improvements," where they should briefly outline whether they were able to address any of the issues highlighted in the main review and provide details of the revisions made. Only minor revisions are permitted; substantial changes are not allowed. Additionally, it is entirely acceptable to report no revisions if the work is already in satisfactory condition.
- The provided reviews will not be shared with any third parties or individuals other than the workshop organizers. Strict adherence to privacy and the double-blind policy will be maintained.
Reviewing Process
Each submission will undergo a rigorous double-blind peer review process. Submissions will be evaluated on criteria such as technical merit, originality, potential impact, and ethics.
Reviewers, including organizers, will not evaluate submissions from individuals who:
- Have been colleagues within the same organization in the past three years.
- Have co-authored publications within the last three years.
- Are currently affiliated with the same institution as the submitting authors.
Publication and Presentation Policies
Accepted papers will be published in the ACM Companion proceedings and presented at the workshop. Papers must be covered by a distinct conference registration and accompanied by a pre-recorded video. All accepted papers are required to be presented in-person.
Program Committee Co-Chairs
-
Dr. Lifu Huang - UC Davis
lfuhuang@ucdavis.edu -
Dr. Dawei Zhou - Virginia Tech
zhoud@vt.edu -
Dr. Adithya Kulkarni - Virginia Tech
aditkulk@vt.edu
Workshop Schedule
The workshop is scheduled to take place during the ACM Web Conference from April 28-29, 2025.
| Sydney NSW Time (GMT+11) | Event |
|---|---|
| 9:00-9:10 | Opening Remarks |
| 9:10-10:40 | Two Keynote Speeches (40 min and 5 min QA each) |
| 10:40-11:55 | Oral paper session (12 min talk + 3 min QA) |
| 11:55-12:10 | Coffee Break |
| 12:10-13:00 | Speed Dating Workshop |
| 13:00-14:30 | Two Keynote Speeches (40 min and 5 min QA each) |
| 14:30-15:30 | Brainstorming and interaction session with speakers and organizers |
| 15:30-15:45 | Coffee Break |
| 15:45-16:30 | Poster Session (10-12 poster boards are required) |
| 16:30-17:15 | Panel Discussion |
| 17:15-17:30 | Closing remarks with awards |
ORGANIZERS
Dr. Lifu Huang
UC Davis
Dr. Danai Koutra
University of Michigan
Dr. Temiloluwa Prioleau
Dartmouth College
Dr. Adithya Kulkarni
Virginia Tech
Dr. Dawei Zhou
Virginia Tech
COMMITTEE MEMBERS
CONTACT US
For inquiries regarding the workshop, please reach out to us at webconf2025agenticai@googlegroups.com.