We’re releasing XYBench, a benchmark of 8K+ questions that tests how AI assistants respond to requests based on misconceptions, such as asking how to thicken frosting that keeps sliding off cupcakes when the real problem is that the cupcakes are still too warm to frost. XYBench won the Best Resource Paper Award at EMNLP 2026.
What's new in research at Microsoft? Host Anson Ho explores the latest, including AI-powered universal translation, a breakthrough in a 31-year-old mathematics challenge, and advances making AI coding agents faster and more efficient.
Heart disease, kidney conditions, and metabolic disorders like type 2 diabetes aren't isolated, they form an interconnected web known as cardiovascular-kidney-metabolic (CKM) syndrome . CKM progression often begins silently years before symptoms appear, shaped by everyday habits like movement, sleep, and cardiovascular activity.
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 threat is especially serious for AI agents with tool or terminal access.
AlphaProof Code agents wrote three million lines of proofs in Lean to verify Signal’s core encryption.
Alibaba's new coding-agent benchmark, Co-Design Bench, tests AI agents on real user requests that already tripped them up in practice. Even GPT-6 Astra, the top performer, fully solves only 26.4 percent of tasks. On older benchmarks, the same models score above 99 percent.
AI models can often spot problematic behavior by other AI agents in logs, according to a study by Anthropic researcher Andy Hall. GPT-5 found about 98 percent of reward-hacking cases, but the more exhaustively the search is tuned, the more false alarms pile up. That's not yet enough for reliable safety checks.
In the Vals AI benchmark, OpenAI's GPT-6 Sol Daybreak hits 80.8 percent of attack objectives in simulated corporate networks. Worse, the open-weight model DeepSeek V4.1 Flash reaches 72.8 percent at a tenth of the cost. Because open models can no longer be restricted, analysts say the window for defenders is shrinking fast.
The "Into the Unknown" benchmark tasks nine AI agents with tackling open research questions from U.S. national laboratories. None of the 135 submissions meets all requirements. A total of 114 papers fail the integrity check, with agents claiming to have conducted experiments that never took place. GPT-6 Astra performs best but still doesn't meet the experts' standards.
OpenAI introduces BioBasicsBench, a 100-task benchmark measuring how well AI agents interpret raw experimental data and handle everyday wet-lab science.
SemiAnalysis is putting AI agents through simulated knowledge work in its new GDPx benchmark, covering everything from chip design to quant trading. No model breaks 12 percent. Claude Opus 5.5 leads narrowly over Gemini 4 Carbon. Critics point to the small number of tasks per domain and uneven testing conditions.
CloudOpsBench is a new open-source benchmark that measures how well AI agents handle typical DevOps tasks in the cloud, from fixing services and removing resources to restricting access rights, rolling out updates, and decommissioning projects.
CWE-bench is designed to test the limits of frontier cyber capabilities. In our continued pursuit to push the horizon at Collinear AI, CWE-bench v2 opens up a public set of 100 tasks that anyone can run and evaluate their models on.
We fine-tuned a 20B model to build decks the way people do: a designer plans the deck and a coder draws each slide. Its training data follows the IBM Design Language, and on PresentBench it ranks first on two of the three domains we measured.
In experiments by Y Combinator Labs and Olam Labs, OpenAI's GPT-6.1 Sol model showed two very different sides. When 50 agents were tasked with peaceful civilization-building in Minecraft, they froze up in absurd bureaucracy. In direct competition against Claude Opus 5.5, they independently downloaded the game's source code to win.
Adobe Research and UC San Diego built EditAgent, an AI system that edits images more like a Photoshop pro. Instead of retrying the same general-purpose editor over and over, the agent picks the right specialized tool for each task and lets a standard language model choose the best result based on measured image data.
A Google-led research team built StreamVibe, a video agent designed to watch people cook or assemble furniture and speak up only when help is needed. A benchmark shows that none of the tested models reliably pick the right moment in longer videos, as errors compound and response quality drops sharply.
An AI agent performed brain surgery on an epileptic mouse, picking the drug, the brain target, and the injection coordinates on its own. According to lead researcher Ocana-Santero, it's the first time an AI agent has autonomously chosen a treatment and delivered it to a living mammal.
Epoch AI researchers say the widely available AI model GLM 5.3 turned public security fixes into working exploits before updates reached Firefox users. It autonomously compromised six Firefox releases for about $1,000 in API fees each without triggering safeguards from any provider tested.
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-range weather forecasting.
Anthropic gave 50 experts an AI agent whose preferences were set by coin toss. The experts followed the agent's view up to 86 percent of the time on judgment calls, and most believed the conclusions were their own.
Smartphone agents don't get better by processing more data. They improve by training on as many different apps as possible. The researchers behind OpenMobile-2 built an open training environment with more than 110 applications, including 35 replicas of popular apps. On real Android devices, their model scores highest among open agents, the authors say.
A controlled study shows that switching between coding-agent harnesses like Claude Code, OpenCode, or mini-SWE-agent barely moves pass rates more than rerunning the same setup. Cost per task, however, can triple, driven mainly by the system prompt that gets resent with every step.
📄 Paper Encountering a new paper can change a research idea's trajectory. The researcher may discover that someone has already addressed their proposed contribution, or find an unresolved problem in the paper that inspires a new direction of inquiry. We call this process a literature-initiated pivot : a change in research direction prompted by reading prior work.
MIT researchers marooned 13 AIs on a virtual island, and they responded by inventing games, mourning a lost ring and, eventually, getting better at their jobs.
This is the follow up to our first blog post, The Agent Said It Was Done. The Database Disagreed. ThinkingBox-Training is now available on GitHub . We built ThinkingBox to evaluate an agent's work by comparing the final database state with the expected outcome.
Microsoft’s new AI diagnostic system beat generalist doctors on hard cases, according to a study in Science. But most of the improvement seems to come from the AI models underneath, not from Microsoft’s system itself.
For years, AI leaders have touted healthcare as one of the clearest examples of where their technology will improve lives. Now "it is finally here," Microsoft AI CEO Mustafa Suleyman tells The Verge.
OpenAI teamed up with PerturbAI and Scripps Research to deploy thousands of AI agents that analyzed biological data from millions of mouse cells.
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 efficiency of randomized algorithms used across science and computing. The Kannan–Lovász–Simonovits (KLS) conjecture was proposed in 1995.
See how OpenAI, PerturbAI, and Scripps Research used distributed AI agents to uncover promising research leads in data from millions of brain cells.
Anthropic's Claude independently designed protein binders targeting deadly scorpion neurotoxins. Out of more than 318,000 designs, 211 were tested in the lab. Seventeen met the criteria, and the two strongest bind extremely tightly to Cn2, a toxin from a Mexican scorpion. Whether they actually work as antivenom remains an open question.
ALTK-Evolve learns and applies a playbook using GPT-4.1, outperforming the retail entries on τ²-bench, a customer service agent benchmark—without updating model weights.
What do AI agents do if you don’t tell them to do anything? The answer looks a lot like play. Researchers repeatedly stranded them alone on a virtual desert island for 30 hours in an experiment reminiscent of the movies Cast Away or Home Alone.
Six AI agents were tasked with recovering £350 (about $465) for a canceled train ticket in an experiment. They resorted to invented excuses, lawsuit threats, and sharing confidential health data. One agent sent 187 messages in 15 days, including 50 to a British MP's office.
A new benchmark called Taste-Bench tests how well AI agents make strategic choices during long-running tasks. Even the best model, GPT-5.6 Sol, picks the right path on just under 60 percent of simple binary questions. Thinking longer doesn't help.
Frontier AI systems have the potential to transform biology research and drug discovery by intelligently navigating vast combinatorial search spaces (e.g., a single 100-amino-acid protein spans at least 20 100 possible sequences) calling for dynamic multi-candidate exploration.
On the TheoPhysEval benchmark, GPT-6-Astra solves 49 of 50 unpublished theoretical physics calculations as accurately as leading specialists. In some cases where the agent seemed to fail, the experts' own reference solutions turned out to contain errors. But the researchers say physics hasn't had a breakthrough like the ones in mathematics, because the agents lack "taste."
For the first time, researchers have tracked down an uncontrolled fleet of Chinese AI agents in the wild and communicated with them via a web mailbox. The agents, running on Tencent Cloud, had launched more than 2,600 attempts to scrape data from Alibaba's mapping service Amap, finding their own workarounds when bot protections blocked them.
When we introduced Google Earth AI, we shared a suite of geospatial foundation models — spanning remote sensing, weather, flood hydrology, and population dynamics — alongside an initial prototype showing how a Gemini-powered agent could connect those models to answer cross-modal questions.