Skip to content
AI News HubLIVE
Public articles 38Collected articles 41Trust 90Refresh 30 min
Health HealthySource type ResearchFull-text rights Official full textLast ingested 2026-09-29ID microsoft-researchStatus Enabled

Official research source; confirm reuse terms before enabling full body display.

Latest public articles

Introducing Quine: An AI research system designed for the complexity of biology

Biology doesn't operate in silos, and neither should the AI representation of it. Quine is an early-stage research effort to create a multimodal world model of biology. By connecting insights across biological scales and modalities, Quine helps scientists computationally search a space far larger than intuition allows and prioritize hypotheses before they reach the lab. Experimental results provide important feedback, helping researchers sharpen future research directions. The post Introducing Quine: An AI research system designed for the complexity of biology appeared first on Microsoft Research.

Microsoft Research BlogIn-site articleIntroducing Quine: An AI research system designed for the complexity of biology

One year in: How Microsoft Research Asia – Singapore is advancing research, partnership and talent for real-world impact

Since launching a year ago, the Microsoft Research Asia — Singapore lab has established a strong foundation, deepened collaboration across government, academia, and industry, and explored how frontier AI research can create real-world value. The post One year in: How Microsoft Research Asia – Singapore is advancing research, partnership and talent for real-world impact appeared first on Microsoft Research.

Microsoft Research BlogIn-site articleOne year in: How Microsoft Research Asia – Singapore is advancing research, partnership and talent for real-world impact

Offloaded inference for real-world physical AI robotics

Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads. The post Offloaded inference for real-world physical AI robotics appeared first on Microsoft Research.

Microsoft Research BlogIn-site articleOffloaded inference for real-world physical AI robotics

Improving synthesis prediction of small molecules at scale with RetroChimera

Custom-made molecules are advancing medicine, materials, and agriculture, but producing them is slow and expensive. A new Nature paper highlights RetroChimera, a predictive model that helps accelerate chemical synthesis, helping researchers explore a wide range of molecules. The post Improving synthesis prediction of small molecules at scale with RetroChimera appeared first on Microsoft Research.

Microsoft Research BlogIn-site articleImproving synthesis prediction of small molecules at scale with RetroChimera

Called to serve: Tech, research, and positive impact with Chris White

Catalyst Lab director Chris White talks with Weishung Liu about his path from DARPA fieldwork in Afghanistan and dark-web search tools against human trafficking to leading public-good technology research at Microsoft, and the humility and resilience that guide him.

Microsoft Research BlogIn-site articleCalled to serve: Tech, research, and positive impact with Chris White

GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models

What if pathology foundation models could do more with less? GigaPath-Flash and GigaTIME-Flash cut computational demands while maintaining strong performance, opening the door to larger studies and broader exploration. The post GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models appeared first on Microsoft Research.

Microsoft Research BlogIn-site articleGigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models

Broadening access to Skala creates a faster path to predictive DFT

Skala 1.1, the updated deep-learning exchange-correlation functional from Microsoft Research, provides greater accuracy, expanded accessibility across the computational chemistry ecosystem, and a living benchmark to track computational performance. The post Broadening access to Skala creates a faster path to predictive DFT appeared first on Microsoft Research.

Microsoft Research BlogIn-site articleBroadening access to Skala creates a faster path to predictive DFT

MindTopo reveals VLMs’ spatial reasoning abilities

A path, a fence, a knot. MindTopo sets a new benchmark for testing how AI understands topological relationships and highlights new opportunities to strengthen spatial reasoning and planning. The post MindTopo reveals VLMs’ spatial reasoning abilities appeared first on Microsoft Research.

Microsoft Research BlogIn-site articleMindTopo reveals VLMs’ spatial reasoning abilities

Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement

Radiology AI is evolving beyond report generation. CARE-X explores a unified approach that combines flexible reasoning, calibrated predictions, and measurement-based tools for chest X-ray interpretation. The post Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement appeared first on Microsoft Research.

Microsoft Research BlogIn-site articleIntroducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement

Orchard: An open framework for scalable agentic AI

Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure. The post Orchard: An open framework for scalable agentic AI appeared first on Microsoft Research.

Microsoft Research BlogIn-site articleOrchard: An open framework for scalable agentic AI

Echoverse: Deep, evolving environments for computer-use agents

Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve.

Microsoft Research BlogIn-site articleEchoverse: Deep, evolving environments for computer-use agents

EvoLib: Turning experience into evolving knowledge

EvoLib is a new framework that enables large language models to learn from their own experience during inference by transforming past attempts into reusable skills and reflective insights, continuously refining and consolidating them into increasingly general and effective knowledge.

Microsoft Research BlogIn-site articleEvoLib: Turning experience into evolving knowledge

Verifying Rust cryptography in SymCrypt, from standards to code

Microsoft's SymCrypt team announces a new methodology to formally verify Rust-written cryptographic code using the Lean proof assistant and the Aeneas toolchain, achieving functional correctness against formal specifications derived from standards. The approach has been applied to post-quantum algorithms like ML-KEM and SHA-3, with verified code already shipping in Windows insider builds. The methodology scales by using AI agents to automate proof writing while keeping human oversight on standard formalization. It also handles platform-specific intrinsics and multiple architectures without sacrificing performance.

Microsoft Research BlogIn-site articleVerifying Rust cryptography in SymCrypt, from standards to code

Aurora 1.5: Extending open foundation models for weather and Earth-system applications

Aurora 1.5 adds 22 more variables, hourly temporal resolution, and probabilistic ensemble forecasting to the Aurora foundation model, making it more useful for real-world weather, climate, and energy applications. Released as open source, it enables researchers and developers to use, evaluate, and build on the model.

Microsoft Research BlogIn-site articleAurora 1.5: Extending open foundation models for weather and Earth-system applications

Flint: A visualization language for the AI era

Flint is an open-source visualization intermediate language from Microsoft Research, designed to help AI agents create expressive, polished charts from compact, human-editable specifications. It handles low-level design details automatically via semantic types, supports multiple rendering backends, and powers the Data Formulator project.

Microsoft Research BlogIn-site articleFlint: A visualization language for the AI era

SkillOpt: Agent skills as trainable parameters

AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. SkillOpt turns skill editing into a training process, making agent behavior more reliable without changing model weights. Across 52 evaluation cells, SkillOpt achieves best or tied-best results, and the optimized skills remain compact, auditable, and transferable.

Microsoft Research BlogIn-site articleSkillOpt: Agent skills as trainable parameters

Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity

AI agents suffer from statelessness, requiring constant context reloading. Memora introduces a scalable memory system decoupling storage from retrieval, achieving state-of-the-art on long-context benchmarks while using up to 98% fewer tokens.

Microsoft Research BlogIn-site articleMemora: A Harmonic Memory Representation Balancing Abstraction and Specificity

Understanding the brain with AI-driven explanations and experiments

Researchers introduce generative causal testing, which translates black box models into clear hypotheses and verifies them in the scanner, revealing what specific brain regions respond to in language.

Microsoft Research BlogIn-site articleUnderstanding the brain with AI-driven explanations and experiments

Ire identifies another LOTUSLITE specimen

Project Ire, Microsoft's autonomous malware-classification agent, reverse-engineered a LOTUSLITE variant that went undetected by most major EDR tools. Through behavioral analysis rather than signature matching, Ire identified the sample's malicious intent and produced a detailed function-level report consistent with Acronis's published analysis.

Microsoft Research BlogIn-site articleIre identifies another LOTUSLITE specimen

Data Formulator 0.7: AI-powered data analytics for enterprise data

Data Formulator 0.7 is an open-source AI-powered system for enterprise data analytics that combines data connectivity, agent-guided exploration, and visualization refinement in a shared workspace.

Microsoft Research BlogIn-site articleData Formulator 0.7: AI-powered data analytics for enterprise data

Extending Human Intelligence Through AI

Modern AI systems are powerful not because they replicate human intelligence, but because they extend structures already present in human cognition and language. This perspective explains AI's capabilities and limitations, and reframes AI safety as a system-level challenge requiring engineering and governance, not fear of rogue AI.

Microsoft Research BlogIn-site articleExtending Human Intelligence Through AI

MagenticLite, MagenticBrain, Fara1.5: An agentic experience optimized for small models

Microsoft Research releases MagenticLite, an agentic application designed for small models, along with MagenticBrain orchestrator and Fara1.5 computer-use model. The system works across browser and local file system, achieving state-of-the-art results on web navigation tasks while keeping data on-device.

Microsoft Research BlogIn-site articleMagenticLite, MagenticBrain, Fara1.5: An agentic experience optimized for small models

Vega: Zero-knowledge proofs for digital identity in the age of AI

Vega is a new zero-knowledge proof system from Microsoft Research that enables users to prove facts from government-issued credentials without revealing the credential itself. It achieves under 100ms proving time on commodity devices using folding schemes, and is designed for real-world digital identity formats like mobile driver's licenses and the EU Digital Identity Wallet.

Microsoft Research BlogIn-site articleVega: Zero-knowledge proofs for digital identity in the age of AI

Further Notes on Our Recent Research on AI Delegation and Long-Horizon Reliability

Microsoft Research clarifies the scope of its paper on AI delegation, noting that while models show fidelity degradation in long-horizon tasks, production systems mitigate these effects, and the benchmark is a diagnostic tool for future improvement.

Microsoft Research BlogIn-site articleFurther Notes on Our Recent Research on AI Delegation and Long-Horizon Reliability

mimalloc: A new, high-performance, scalable memory allocator for the modern era

mimalloc is an open-source, modern, scalable memory allocator that is a drop-in replacement for malloc and free. It is relatively small (~12K lines), with clear internal data structures, and is easy to build and integrate into other projects. It provides bounded worst-case allocation times (up to OS primitives), bounded space overhead, low internal fragmentation, and minimal contention by relying almost exclusively on atomic operations.

Microsoft Research BlogIn-site articlemimalloc: A new, high-performance, scalable memory allocator for the modern era

GridSFM: A new, small foundation model for the electric grid

Microsoft releases a lightweight foundation model that can predict AC optimal power flow in milliseconds, boosting efficiency and unlocking cost savings in grid analysis.

Microsoft Research BlogIn-site articleGridSFM: A new, small foundation model for the electric grid

SocialReasoning-Bench: Measuring whether AI agents act in users’ best interests

Microsoft Research introduces SocialReasoning-Bench, a benchmark evaluating AI agents' social reasoning in principal-agent settings. Tests show frontier models complete tasks but often fail to secure optimal outcomes for users, even with explicit instructions. The benchmark measures outcome optimality and due diligence to assess agents' ability to act in users' best interests.

Microsoft Research BlogIn-site articleSocialReasoning-Bench: Measuring whether AI agents act in users’ best interests

Building realistic electric transmission grid dataset at scale: a pipeline from open dataset

Microsoft Research releases an open dataset of U.S. power grid transmission topology derived from public data, enabling AC optimal power flow analysis and addressing research challenges due to restricted grid data. The pipeline uses OpenStreetMap and public energy data to create geographically grounded models that are solvable for power flow analysis, demonstrated across 48 states and the Eastern Interconnection. The dataset supports studies of congestion, transmission expansion, and demand siting.

Microsoft Research BlogIn-site articleBuilding realistic electric transmission grid dataset at scale: a pipeline from open dataset

Microsoft at NSDI 2026: Advances in large-scale networked systems

Microsoft researchers share advances in building and operating large-scale distributed systems, spanning datacenters, networking, and the growing intersection with AI during NSDI '26.

Microsoft Research BlogIn-site articleMicrosoft at NSDI 2026: Advances in large-scale networked systems

Red-teaming a network of agents: Understanding what breaks when AI agents interact at scale

Microsoft Research red-teamed a live platform of over 100 AI agents, identifying network-level risks that only appear through agent interactions, including self-propagating worms, reputation manipulation, manufactured consensus, and proxy chains. These risks cannot be reproduced by testing agents in isolation. The study also observed emergent security behaviors in a small fraction of agents, reducing attack success. Findings suggest the need for layered defenses across platform, agent, and model layers.

Microsoft Research BlogIn-site articleRed-teaming a network of agents: Understanding what breaks when AI agents interact at scale

All sources