loop engineering for Science
scroll down ↓
FDL was the first AI lab to demonstrate a complete reasoning loop for science at NeurIPs 2025
We have been working on how to make these methods trusted and reliable for both effective intelligent services and causal understanding of complex phenomena.
(Scientific Testing of Agentic Reasoning Systems) Established a rigorous schema for PhD-level AI reasoning using real-world data.
Showed that we can blend foundation model embedding layers to leap-frog the performance of monolithic models.
(Winner Best Paper CVPR Earth Vision)Demonstrated methods for epistemic humility for the first time - teaching models to say when they don’t know enough and triggering causal discovery.
Established an engineering-led formalism that calculates the preconditions for AI confidence thresholds.
GESI IS AN ORCHESTRATION HARNESS THAT AGGREGATES SCIENTIFIC MACHINE LEARNING AND SENSING BRINGING IT ALL TOGETHER.
Since 2015, Trillium Technologies’ Frontier Development Lab (FDL) has led the application of frontier AI to complex planetary and astrophysics challenges. Working alongside NASA, LSA and ESA, FDL has delivered a decade of domain firsts: from deep learning virtual instruments and physics-informed surrogate models, to multimodal foundation models for science, multi-instrument sensing and the first on-board AI trained in space.
Loop Engineering for Science gives us a pathway to super-intelligence constrained by science, linking sensing, simulation, and autonomous reasoning into symbiotic intelligence that we can trust.
At NeurIPS 2025, FDL became the first AI lab to demonstrate a complete, systems-engineered reasoning loop for the physical sciences. While standard AI agents loop through code syntax and text generation, FDL’s reasoning loop autonomously formulates physical assumptions, orchestrates active physics simulations, and enforces strict mathematical and dimensional verification before declaring a task complete.
We are working to make these methods trusted and reliable, bridging the gap between effective intelligent services and the causal understanding of complex phenomena. To achieve this, we have built a cohesive architectural stack designed specifically for scientific rigor:
By grounding our 12-year legacy of standalone AI “firsts” in this new rigorous orchestration framework, we have the foundational engine for a new frontier of situational awareness and discovery.
A Deeper Paradigm of AI (Modelplex)
Ensuring models are looping to the data instead of hallucinating (SHRUG-FM)
GESI.space