Loading...
Organizing Committee
MIT
Atomic Machines and Stanford University
Brown University
Brown University
Johns Hopkins University
Abstract
The workshop on Agentic Scientific Computing and Scientific Machine Learning will examine the emerging mathematical, systems theory, and information theory foundations of agent-based AI systems embedded within scientific and engineering workflows. Recent advances in foundation models, reinforcement learning, and automated reasoning are enabling AI agents that can design experiments, select models, run simulations, and analyze results in iterative closed-loop pipelines. While early demonstrations of such systems are rapidly appearing across physics, materials science, fluid dynamics, and computational biology, their mathematical structure and theoretical properties remain largely unexplored. This workshop will bring together researchers in applied mathematics, scientific computing, machine learning, and engineering to investigate the mathematical principles underlying agentic scientific workflows, including connections to control theory, optimization, inverse problems, and uncertainty quantification. By focusing on formal models, algorithmic frameworks, and rigorous evaluation methodologies, the workshop aims to help establish a principled foundation for agent-based approaches to next-generation scientific computing and machine learning.
Loading...
Loading participant list in background...
Workshop Schedule
Saturday, May 09, 2026
8:30 - 8:50 AM EDT
Check In
11th Floor Collaborative Space
8:50 - 9:00 AM EDT
Welcome from ICERM Director
Welcome - 11th Floor Lecture Hall
9:00 - 9:45 AM EDT
TBA
11th Floor Lecture Hall
Speaker
Bogdan Georgiev, Google Deepmind
Session Chair
George Karniadakis, Brown University
10:00 - 10:15 AM EDT
Coffee Break
11th Floor Collaborative Space
10:15 - 11:00 AM EDT
The Denario project: Deep knowledge AI agents for scientific discovery
11th Floor Lecture Hall
Speaker
Francisco Villaescusa-Navarro, Simons Foundation
Session Chair
George Karniadakis, Brown University
Abstract
Science advances by formulating and testing hypotheses, collecting and analyzing data, and drawing conclusions—yet much of a scientist’s time is spent in tasks such as coding analyses, writing and revising text, reviewing the literature, and learning new concepts. Can recent advances in AI help reclaim some of that time? In this talk, I will show how large language models and AI agents may help scientists with these tasks. I will present Denario, a complex, publicly available, multi-AI-agent system designed to function as a research assistant. Developed and evaluated by a diverse team of scientists, mathematicians, and philosophers, Denario is an interdisciplinary tool capable of generating ideas, searching the literature, developing research plans, writing and executing code, crafting plots, drafting and reviewing scientific papers. I will present and discuss some of the documents generated by Denario in disciplines such as astrophysics, biology, biophysics, biomedical informatics, chemistry, machine learning, material science, mathematical physics, medicine, neuroscience, planetary physics, and quantum physics. I'll finalize discussing the benefits and perils of automating (parts) of science.
11:15 AM - 12:00 PM EDT
Less Data, More Knowledge: Semantic Communication and Emergent Protocols for Reasoning-Driven Intelligent Systems
11th Floor Lecture Hall
Speaker
Walid Saad, Virginia Tech
Session Chair
George Karniadakis, Brown University
Abstract
Traditionally, communication has been treated as the reliable transfer of data between entities, with the goal of reproducing messages as faithfully as possible, independent of meaning or downstream utility. While effective in classical systems, this data-centric paradigm becomes limiting in modern intelligent environments involving distributed decision-making, multi-agent interaction, and large-scale coordination, where what matters is not only what is transmitted, but what is meant and how it is used. In this talk, we focus on semantic communication protocols as a general paradigm for information exchange in intelligent systems, with applications spanning wireless networks and beyond. These protocols go beyond symbol fidelity to enable meaning-aware, task-driven interaction under strict resource constraints, operating over shared latent structure rather than raw data. We discuss how such protocols can be learned and optimized, and how they naturally extend across a broad range of applications, including agentic AI systems, where coordination, reasoning, and adaptation emerge through interaction rather than explicit design. We present a unified perspective grounded in artificial intelligence, causal reasoning, game theory, and theory of mind, where communication, inference, and control are jointly learned processes. Within this framework, we highlight three directions: emergent semantic communication via signaling games and neuro-symbolic reasoning, where efficient protocols arise from interaction; causal semantic communication in digital twin and wireless network systems that exploits invariances for robust control; and multi-agent world models with metacognitive reasoning, where agents infer and adapt to others’ beliefs and intentions without explicit communication, leading to emergent collective behavior. Collectively, these results point toward a shift from engineered communication protocols to learned, adaptive, and emergent semantic interaction systems, where meaning and reasoning become first-class design principles.
12:15 - 1:15 PM EDT
Lunch provided by ICERM
Working Lunch - 11th Floor Collaborative Space
1:15 - 2:00 PM EDT
Adaptive Swarms Across Scales
11th Floor Lecture Hall
Speaker
Markus J. Buehler, MIT
Session Chair
Marta D'Elia, Atomic Machines and Stanford University
Abstract
AI is rapidly transitioning from a passive analytical assistant to an active, self-improving partner in scientific discovery. In the material world, this shift means developing systems that not only recognize patterns but also reason, hypothesize, and autonomously explore new ideas for design, discovery and manufacturing. This talk presents emerging approaches toward 'superintelligent' discovery engines -integrating reinforcement learning, graph-based reasoning, and physics-informed neural architectures with generative models capable of cross-domain synthesis. We explore multi-agent swarm systems inspired by collective intelligence in nature, enabling continuous self-evolution as they solve problems. Case studies from materials science, engineering and biology illustrate how these systems can uncover hidden structure-property relationships, design novel materials, and accelerate innovations in biology and beyond. These advances chart a path toward AI that actively expands the boundaries of human knowledge.
2:15 - 3:00 PM EDT
Force-Conditioned Video Models as Physical World Models for Agents
11th Floor Lecture Hall
Speaker
Chen Sun, Brown University
Session Chair
Marta D'Elia, Atomic Machines and Stanford University
Abstract
A central challenge in agentic scientific computing is equipping agents with world models that can accurately simulate the physical consequences of actions. Recent advances in video generation models have sparked interest in using video to simulate such physical causes and effects. In this talk, we investigate using physical forces as a conditioning signal for video generation, which enable users and agents to interact with images and videos through both localized point forces, such as poking a plant, and global force fields, such as wind blowing on fabric. We demonstrate that these "force prompts" can enable videos to respond realistically to physical control signals by leveraging the visual and motion priors in the original pretrained model, without using any 3D asset or physics simulator at inference time. The primary challenge of force prompting is the difficulty in obtaining high-quality paired force-video training data, both in real-world data, due to the difficulty of obtaining force signals, and in synthetic data, due to limitations in the visual quality and domain diversity of physics simulators. Our key finding is that video generation models can generalize remarkably well when adapted to follow physical force conditioning using only synthetic videos. Building on this, we explore the role of such force-conditioned world models in robot planning and decision-making.
3:15 - 4:00 PM EDT
4:00 - 4:45 PM EDT
Building a Science Assistant
11th Floor Lecture Hall
Speaker
Michael Brenner, Harvard University
Session Chair
Marta D'Elia, Atomic Machines and Stanford University
Abstract
The way we do (computational and theoretical) science is undergoing a transformation. I will discuss our recent efforts to build a science assistant, focusing on the manual creation of software to support computational and theoretical experiments. To this end we built an AI system that creates expert-level scientific software whose goal is to maximize a quality metric. I will go through a wide set of examples, from epidemiological forecasting to computational biology, to theoretical physics, to engineering
5:00 - 6:30 PM EDT
Reception
11th Floor Collaborative Space
Sunday, May 10, 2026
9:00 - 9:45 AM EDT
TBA
Virtual
Virtual Speaker
Susmit Jha, Defense Advanced Research Projects Agency (DARPA)
Speaker
Yannis Kevrekidis, Johns Hopkins University
Session Chair
Francisco Villaescusa-Navarro, Simons Foundation
10:00 - 10:45 AM EDT
Advancing science and medicine with collaborative AI agents
11th Floor Lecture Hall
Speaker
Vivek Natarajan, Google
Session Chair
Francisco Villaescusa-Navarro, Simons Foundation
Abstract
This talk introduces general-purpose AI systems from Google DeepMind designed to accelerate scientific discovery and democratize medical expertise. First, the AI co-scientist, a multi-agent Gemini-based system, assists researchers by systematically generating and refining novel hypotheses for complex scientific challenges. This approach has yielded promising, lab-validated results, including identifying drugs for repurposing against acute myeloid leukemia, discovering new therapeutic targets for liver fibrosis (Advanced Science), and recapitulating a novel gene transfer mechanism for bacterial resistance (Cell). While early, the co-scientist represents a promising step toward a true collaborative AI partner for scientist. Secondly, the AI co-physician, AMIE, aims to give doctors superpowers and make medical expertise universally accessible. In simulated settings, AMIE outperformed primary care physicians across multiple clinical evaluation axes (Nature) and is showing promise as an assistive tool in ongoing real-world validations (Nature). Together, these initiatives demonstrate AI's potential to transform scientific research and care delivery.
10:55 - 11:00 AM EDT
Group Photo (Immediately After Talk)
11th Floor Lecture Hall
11:00 - 11:30 AM EDT
Coffee Break
11th Floor Collaborative Space
11:30 AM - 12:15 PM EDT
Role-Specialized Agentic Orchestration for Adaptive Learning and Trustworthy Verification and Validation
11th Floor Lecture Hall
Speaker
Guang Lin, Purdue University
Session Chair
Francisco Villaescusa-Navarro, Simons Foundation
Abstract
The talk introduces an agentic AI framework centered on how role-specialized LLM agents can support decision-making, adaptation under non-stationary environment, and system validation and verification (V&V) for trustworthy autonomous system. Our framework provides two complementary directions. First, ATLAS proposes agentic self-evolution, where an evolving agent within the core algorithm EvoDPO is improved over a long-horizon by task-distributed supporter LLM agents responsible for exploration, fine-tuning strategy, and adaptive reference-policy gating mechanism. This project targets progressive agent development under drifting environment and demonstrates domain adaptation for sustained improvement in changing domains, such as non-stationary bandits and scientific machine learning. Second, AIVV conducts agentic verification and validation, where mathematically grounded anomaly detection is strictly validated by role-specialized LLM agents that verify failure modes of the system again natural-language requirements. This framework distinguishes nuisance faults from true faults and produces actionable engineering protocols, such as gain-tuning parameter proposals. Together, these projects define a common paradigm: Agentic AI as a structured orchestration that combines statistical or optimization-based inner loops with role-based LLM oversight to achieve scalable adaptation, reliability, and safety. This perspective moves beyond viewing LLM agents as standalone assistants, instead positioning them as coordinating components for progressive self-improving, and trustworthy system V&V intelligent systems.
12:30 - 2:00 PM EDT
Lunch/Free Time
2:00 - 2:45 PM EDT
Turning thoughts into things
11th Floor Lecture Hall
Speaker
Erik Peterson, Atomic Machines
Session Chair
Yannis Kevrekidis, Johns Hopkins University
Abstract
Can language agents turn informal words into working, complex physical machines, like MEMS devices? Not directly, and not yet: the physics is too intricate, complex devices have too many parts, assembly planning for complex 3D devices is computationally hard, and the public training data is too thin for manufacturable designs, especially if the aim is production use. I will discuss an approach that treats agents and other generative models not as free-form inventors, but as elements in a generate-to-solve pipeline: they help turn informal design intent into a series of formal representations, then hand those representations piecewise to simulators, solvers, compilers, and validators that enforce physical, geometric, material, and process constraints. I will show early results from this pipeline where agents help convert rough design intent into formal problems that classical and generative tools can solve, check, and optimize.
3:00 - 3:20 PM EDT
Agenticsciml: Collaborative multi-agent systems for emergent discovery in scientific machine learning
11th Floor Lecture Hall
Speaker
Qile Jiang, Brown University
Session Chair
Yannis Kevrekidis, Johns Hopkins University
Abstract
We introduce AgenticSciML, a collaborative multi-agent system in which over 10 specialized AI agents collaborate to propose, critique, and refine SciML solutions through structured reasoning and iterative evolution. Across physics-informed learning and operator learning tasks, the framework discovers solution methods that outperform single-agent and human-designed baselines by up to four orders of magnitude in error reduction. The agents produce novel strategies -- including adaptive mixture-of-expert architectures, decomposition-based PINNs, and physics-informed operator learning models -- that do not appear explicitly in the curated knowledge base. These results show that collaborative reasoning among AI agents can yield emergent methodological innovation, suggesting a path toward scalable, transparent, and autonomous discovery in scientific computing.
3:25 - 3:45 PM EDT
ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms
11th Floor Lecture Hall
Speaker
Juan Toscano, Brown University
Session Chair
Yannis Kevrekidis, Johns Hopkins University
Abstract
Progress in computational science depends on complex numerical workflows that must faithfully encode physical laws, yet translating conceptual insight into reliable code remains a major bottleneck. Although large language models can generate isolated code fragments, they lack the structured reasoning required to design, verify, and iteratively refine complete scientific pipelines. Here we introduce ATHENA, an agentic framework explicitly designed to emulate scientific research modeled as a knowledge-driven contextual bandit process. Its core loop separates conceptual policy from numerical realization through expert-derived conceptual scaffolding, enabling principled diagnosis, reformulation, and repair of computational strategies. Across scientific computing and scientific machine learning tasks, ATHENA autonomously discovers exact analytical solutions, constructs stable numerical solvers, diagnoses ill-posed formulations, and orchestrates hybrid symbolic–numeric workflows. Quantitatively, ATHENA exceeds expert-designed workflows, achieving superhuman accuracy and robustness on canonical benchmarks. By reframing computation as an object of agentic reasoning, our framework enables autonomous orchestration of heterogeneous algorithms across scientific domains.
4:00 - 4:45 PM EDT
Multiagent Systems for Scientific Discovery
11th Floor Lecture Hall
Speaker
Yilun Du, Harvard University
Session Chair
Yannis Kevrekidis, Johns Hopkins University
Abstract
I'll discuss how multi-agent systems are effective tools for scientific discovery. I'll first present a series of ways to build multi-agent language model systems, such as having systems that can debate with each other, verify each others responses, or define a search objective to optimize across agents. I'll illustrate some of the benefits of multi-agent systems and how they allow us to build a more self-improving overall system.
5:00 - 6:30 PM EDT
Conclusion & Coffee Break
Coffee Break - 11th Floor Collaborative Space
Request Reimbursement
This section is for general purposes only and does not indicate that all attendees receive funding. Please refer to your personalized invitation to review your offer.
- Acceptable Costs
- 1 roundtrip between your home institute and ICERM
- Flights in economy class to either Providence airport (PVD) or Boston airport (BOS)
- Ground Transportation to and from airports and ICERM.
- Unacceptable Costs
- Seats in economy plus, business class, or first class
- Change ticket fees of any kind
- Multi-use bus passes
- Meals or incidentals
- Advance Approval Required
- Personal car travel to ICERM from outside New England
- Multiple-destination plane ticket; does not include layovers to reach ICERM
- Arriving or departing from ICERM more than a day before or day after the program
- Multiple trips to ICERM
- Rental car to/from ICERM
- Arriving or departing from airport other than PVD/BOS or home institution’s local airport
- 2 one-way plane tickets to create a roundtrip (often purchased from Expedia, Orbitz, etc.)
- Travel Maximum Contributions
- New England: $350
- Other contiguous US: $850
- Asia & Oceania: $2,000
- All other locations: $1,500
- Note these rates were updated in Spring 2023 and supersede any prior invitation rates.
- Reimbursement Requests
Request Reimbursement with Cube
Refer to the back of your ID badge for more information. Checklists are available at the front desk and in the Reimbursement section of Cube.
- Reimbursement Tips
- Scanned original receipts are required for all expenses
- Airfare receipt must show full itinerary and payment
- ICERM does not offer per diem or meal reimbursement
- Allowable mileage is reimbursed at prevailing IRS Business Rate and trip documented via Google Maps PDF
- Keep all documentation until you receive your reimbursement!
- Reimbursement Timing
6–8 weeks after all documentation is sent to ICERM. All reimbursements are reviewed by multiple Brown University offices.
- Reimbursement Deadline
Submissions must be received within 30 days of ICERM departure to avoid applicable taxes. No submissions are accepted after six months.