Research Lab

The Lab:
Curiosity in Action

Academic-grade research on multi-agent AI, clinical systems, and cognitive architectures. These are living documents—we publish questions as much as answers, and document our dead ends with the same rigor as our successes.

Open Development
Live Documentation
Collaborative Research
9Research Papers

Research Projects

Click any project to view full documentation, methodology, and real-time findings.

Published
Multi-Agent AI
v1.0.0Updated: Nov 27, 2025

Cognitive Temporal Orchestration: Autonomous Multi-Agent Systems for High-Dimensional Constraint Satisfaction in Executive Resource Allocation

Executive calendar management represents a constraint satisfaction problem characterized by high dim...

Executive calendar management represents a constraint satisfaction problem characterized by high dimensionality, conflicting objectives, and dynamic updates. Traditional LLMs fail on complex scheduling (0.6% success on TravelPlanner). This research introduces the Cognitive Temporal Orchestration (CTO) framework—a hybrid architecture integrating heterogeneous LLM orchestration (GPT-5, Gemini 3 Pro, Claude Sonnet 4.5) with CP-SAT constraint programming. Through 81 test scenarios, we demonstrate 100% orchestration success, 100% high-value event identification, and 29.4% cost reduction. Critical analysis reveals 99% of latency originates from LLM inference, fundamentally informing optimization strategies. We validate three cognitive modules establishing a methodology for evaluating evolution from reactive assistants to proactive wealth management systems.

Multi-Agent SystemsConstraint SatisfactionHeterogeneous LLM ArchitectureTemporal ReasoningCalendar Intelligence+5 more
Dr. Saad Jamal, Astrointelligence Research Team
1 update
Published
Clinical AI
v1.0.0Updated: Nov 26, 2025

Comparative Analysis of Large Language Models for Clinical Decision Support: An Ivy League Research Study

This comprehensive evaluation of the Vitruviana Hybrid AI Architecture for clinical decision support...

This comprehensive evaluation of the Vitruviana Hybrid AI Architecture for clinical decision support analyzes model selection patterns, service integration, and clinical outcomes across 100+ automated tests. The hybrid architecture achieved 94.7% system reliability with intelligent task routing, demonstrating 100% optimal routing decisions and directing complex clinical reasoning to Gemini 3 Pro (67% of tasks) and structured tasks to GPT-5.1 (33% of tasks).

Hybrid AI ArchitectureClinical Decision SupportModel SelectionGemini-3-ProGPT-5.1+3 more
Vitruviana Clinical Intelligence Laboratory, AI Research Team
1 update

Our Research Philosophy

We believe research should be transparent, iterative, and immediately useful. Rather than publishing only polished final results, we share our work-in-progress—including failures, pivots, and unexpected discoveries.

Each research project on this page is a living document. As we gather data, refine methodologies, and draw conclusions, the documentation updates in real-time. Version history and changelogs are maintained for full transparency.

Principles

  • Evidence over assumptions — All claims backed by data
  • Reproducibility — Methods documented for replication
  • Open development — Progress shared as it happens
  • Practical application — Research that solves real problems