Orchard: An open framework for scalable agentic AI
03/08/2026 16:00 – Microsoft Research
At a glance Orchard is an open-source framework for scalable and cost-effective agentic AI research, built around Orchard Env, a reusable environment service for training…
Echoverse: Deep, evolving environments for computer-use agents
30/07/2026 17:00 – Microsoft Research
Scaling fidelity over sheer count, targeting the capabilities agents actually lack, and evolving with the models they train. At a glance We built twelve training…
EvoLib: Turning experience into evolving knowledge
30/07/2026 16:00 – Microsoft Research
At a glance Self-supervised. EvoLib enables large language models to learn from their own experience during inference, without requiring ground-truth labels or external feedback. From…
Verifying Rust cryptography in SymCrypt, from standards to code
13/07/2026 16:00 – Microsoft Research
How Rust, Lean, Aeneas, and AI agents are helping scale formal verification for production cryptographic algorithms At a glance SymCrypt develops new verified cryptography using…
Aurora 1.5: Extending open foundation models for weather and Earth-system applications
09/07/2026 16:46 – Microsoft Research
At a glance Aurora 1.5 is a major extension of Microsoft’s Aurora Earth System foundation model that adds 22 more weather variables relevant to energy,…
Flint: A visualization language for the AI era
08/07/2026 16:00 – Microsoft Research
At a glance Polished charts from simple specs. Flint allows AI agents to reliably generate expressive, visually polished charts from simple, human-editable specifications. Semantic types guide…
SkillOpt: Agent skills as trainable parameters
30/06/2026 16:50 – Microsoft Research
At a glance AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. SkillOpt turns skill editing into…
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
29/06/2026 21:14 – Microsoft Research
At a glance Today’s AI agents don’t remember past interactions. They must repeatedly be fed relevant information or retrieve it from external sources, which becomes…
Understanding the brain with AI-driven explanations and experiments
25/06/2026 16:00 – Microsoft Research
At a glance LLM-based models can predict the human brain’s responses to language with high accuracy. But what drives that performance is essentially unreadable: a…
Talos: Scaling rare disease diagnosis with automated, iterative genomic reanalysis
24/06/2026 14:00 – Microsoft Research
At a glance Talos is an open-source tool for automated, iterative reanalysis of genomic data in rare disease. It efficiently re-examines stored sequencing data as scientific…
