Reading room.
Engineering blogs & AI research
A reading room from engineering teams and AI labs: titles, short feed excerpts, and links to the originals. For my own essays, explore the writing archive.
- 1359 articles tracked
- 37 sources
- Refresh scheduled daily
Sources
Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents
Microsoft researchers have discovered Lazarus, a backdoor technique that can reprogram dormant neurons in an AI model, causing an otherwise normal AI agent to execute malicious commands when a hidden trigger appears. The…
Formally verifying agent-written full-stack web apps with PDD Kit
AI agents can generate code at a scale that’s hard for humans to review line-by-line. PDD Kit helps ensure the code is doing what the developer intended by creating formal specifications and testing against them. It conv…
Learn the rules: The hacker mindset
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agilit…
From synthetic enterprise data evaluations to real Microsoft Copilot AI confidence
Evaluating Microsoft Copilot at enterprise scale requires test data that captures the full complexity of real organizations, yet real enterprise data contains sensitive information that cannot be used for evaluation unde…
Microsoft Research Focus – Edition #97
Host Sowbhagya Suresh shares some of the latest news and cutting-edge research from across Microsoft—from understanding the challenges facing coding agents to uncovering how people use AI at work and improving extended-r…
Flint-interactive: A language for creating interactive data visualizations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interac…
Solving a 31-year-old grand challenge in mathematics – the KLS conjecture
For decades, a fundamental question about the difficulty of computing in high-dimensional spaces has resisted proof. New research resolves this question, removing a major theoretical obstacle to understanding the efficie…
Called to serve: Tech, research, and positive impact
Lab Director Chris White has worked on research challenges with real-world implications—from new approaches to wartime data analysis to tools for combating human trafficking. He talks to program manager Weishung Liu abou…
Proof-based general-purpose computing with Magnetar
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains,…
Simulating student learning for better AI tutoring
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across s…
Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it ea…
What AI gets wrong and what failure teaches us
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures”…
Forecasting space weather risks on power grids
Extreme space-weather events can damage power systems on Earth and degrade GPS accuracy and satellite operations. A new machine learning system can predict where damage is likely to occur 30-60 minutes before a storm arr…
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…
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 cre…
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 advanc…
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,…
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. T…
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 trac…
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 VLM…
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 Introdu…
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 r…
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 t…
EvoLib: Turning experience into evolving knowledge
LLMs do not get smarter just by remembering more. EvoLib turns experience into evolving knowledge, taking reusable skills and insights that help models learn and adapt across tasks long after deployment. The post EvoLib:…
Verifying Rust cryptography in SymCrypt, from standards to code
Cryptographic code supports vital protections in modern computing systems. Learn how a new method helps verify code as developers write it while preserving speed and adaptability as it gets implemented and evolves. The p…
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. The po…
Flint: A visualization language for the AI era
Short chart specifications are easy to write, but often produce uninspiring results. Flint is an open-source visualization language that offers a middle path, letting AI agents create expressive charts from compact, huma…
SkillOpt: Agent skills as trainable parameters
AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. Learn how SkillOpt turns skill editing into a training process, making agent behavior more reliable with…
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
AI agents can't remember past conversations. They must constantly reload or retrieve context, which grows less efficient as tasks get longer and more complex. Memora solves this with a scalable memory system separating w…
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. The post Understand…
Talos: Scaling rare disease diagnosis with automated, iterative genomic reanalysis
Talos was built to help resolve a major bottleneck in genomic medicine: human review time. The open-source system recovered 90% of in-scope diagnoses while surfacing just 1.3 candidate variants per patient for expert rev…
Ire identifies another LOTUSLITE specimen
Project Ire examined a timely malware sample and determined its intent through reverse engineering—identifying LOTUSLITE characteristics even as most major EDR tools did not detect it. The post Ire identifies another LOT…
Data Formulator 0.7: AI-powered data analytics for enterprise data
Data Formulator introduces AI-powered analytics for enterprise data workflows. Data teams can easily bring enterprise data into an AI-ready workspace where users can explore, analyze, and visualize data with AI agents to…
Extending Human Intelligence Through AI
Understanding AI as an extension of human intelligence—not a replacement for it—offers a more grounded path for building trustworthy AI systems. The post Extending Human Intelligence Through AI appeared first on Microsof…
MagenticLite, MagenticBrain, Fara1.5: An agentic experience optimized for small models
MagenticLite is an agentic system for small models that works across the browser and local file system in a single workflow. It combines specialized models and orchestration to support efficient agentic performance on ev…
Vega: Zero-knowledge proofs for digital identity in the age of AI
Vega turns a full credential into a single proof, sharing only what is needed and nothing more, with performance that works in real apps. The post Vega: Zero-knowledge proofs for digital identity in the age of AI appeare…
Further Notes on Our Recent Research on AI Delegation and Long-Horizon Reliability
Our recent paper, “LLMs Corrupt Your Documents When You Delegate”, has generated discussion about the reliability of AI systems in delegated workflows. We appreciate the interest in this work and want to clarify several…
GridSFM: A new, small foundation model for the electric grid
Introducing GridSFM, a small foundation model that can predict AC optimal power flow in milliseconds, boosting efficiency and unlocking cost savings. Learn how GridSFM gives grid operators direct visibility into congesti…
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 integrat…
Advancing AI for materials with MatterSim: experimental synthesis, faster simulation, and multi-task models
MatterSim is expanding what AI can do for materials science—from faster large-scale simulations to MatterSim-MT, a new multi-task model for simulating properties beyond potential energy surfaces alone. The post Advancing…
SocialReasoning-Bench: Measuring whether AI agents act in users’ best interests
Using SocialReasoning Bench, we observed a stable pattern across models—agents execute competently, but fail to consistently improve the user’s position, even with explicit instructions to optimize for user interest. The…