AI agents can't remember past conversations. They must constantly reload or retrieve context, which ... - 惯性聚合

推荐订阅源

CERT Recently Published Vulnerability Notes

Forbes - Security

Exploit-DB.com RSS Feed

LINUX DO - 最新话题

The Hacker News

Google Online Security Blog

KPMG report finds enterprise disconnect between AI and its ROI | CIO

The Last Watchdog

Schneier on Security

Troy Hunt's Blog

News | PayPal Newsroom

cs.CL updates on arXiv.org

Schneier on Security

Privacy & Cybersecurity Law Blog

Tor Project blog

Threat Intelligence Blog | Flashpoint

Secure Thoughts

Proofpoint News Feed

cs.CV updates on arXiv.org

Security Latest

Security Archives - TechRepublic

PCI Perspectives

cs.AI updates on arXiv.org

Hacker News - Newest: "LLM"

LINUX DO - 热门话题

Palo Alto Networks Blog

www.infosecurity-magazine.com

Google DeepMind News

Vulnerabilities – Threatpost

Threat Research - Cisco Blogs

OSCHINA 社区最新新闻

News and Events Feed by Topic

TaoSecurity Blog

大猫的无限游戏

钛媒体：引领未来商业与生活新知

Visual Studio Blog

Hacker News: Front Page

Simon Willison's Weblog

Microsoft Research(@MSFTResearch)

Microsoft Research (@MSFTResearch) on X Short chart specifications are easy to write, but often produce uninspiring results. Flint is an ope... Among Microsoft’s 100+ accepted papers, 3 oral presentations, and 1 expo demo at ICML in Seoul, high... AI agents often fail because their instructions, or skills, are manually modified with no guarantee ... What do people actually do with AI at work? A new analysis of five million M365 Copilot conversation... Researchers introduce generative causal testing, which translates black box models into clear hypoth... Talos was built to help resolve a major bottleneck in genomic medicine: human review time. The open-... On the Microsoft Research Podcast, Microsoft’s Jaime Teevan, Jenna Butler, Jake Hofman, and Rebecca ... Can you remember a new password after listening to five hours of stories? A transformer can. AI... ResNet has received the Longuet-Higgins Prize at CVPR 2026, recognizing research with proven, lastin... 30x faster analytics, GPU kernels generated automatically from SQL, AI matched to lab-grown tumor mo... Project Ire examined a timely malware sample and determined its intent through reverse engineering—i... A new research effort called Encrypted Spaces explores an architecture for collaborative application... New research in Nature Methods from Project Ex Vivo shows AI models learn more from diverse cell sta... A BTS look a first timer's experience at the MSR lab at Microsoft Build 2026—featuring the demos, th... During the Inside Azure Innovations breakout at Build 2026, Microsoft Azure CTO, deputy CISO and tec... That’s a wrap on Microsoft Build 2026. Huge thank you to the researchers and team who brought it to ... What do the people who build the foundations for others to build on like to build themselves? The an... You don’t have to be a developer. You can just build stuff. @shanselman on his first walk through th... The sights and sounds of Microsoft Research at #MSBuild. Come see us at the Lab inside the Gateway P... A three‑month pilot in a Midwestern bottling plant shows what happens when AI moves beyond chat and ... Day 1 of Microsoft Build is a wrap. A lot happened today, and we brought some of our favorite tools ... Weather forecasts thousands of times faster than traditional supercomputers. Hear from Kenji Takeda ... Learn more: https://t.co/wzorfOOrof Agentic experiences powered by small models that fit on your own device. Hear from Maya Murad on Mag... Microsoft Research is at BUILD 2026 this week, giving developers a hands-on look at some of the many... Welcome to Microsoft Build 2026. Step inside the Microsoft Research Lab, where developers are getti... Microsoft Research is at #MSBuild!   Come check out the Microsoft Research Lab on the 1st Floor of t... Evaluating agentic behaviors at scale, making the case for repositories over documents, and inviting... Data Formulator introduces AI-powered analytics for enterprise data workflows. Data teams can easily... Understanding AI as an extension of human intelligence—not a replacement for it—offers a more ground... Can AI reason about human values with real-world complexity? Microsoft Research Asia's new Global AI... Vega turns a full credential into a single proof, sharing only what is needed and nothing more, with... Modern apps and services manage memory at a scale that didn't exist a decade ago. mimalloc is the op... Equipping communities to influence AI through involvement in AI development pipelines can improve AI... New in Research Focus: Cloud efficiency, smarter agentic cost reduction, a randomized trial on 3D te... New tools, models, repos, and papers out of Microsoft Research are here. Use AI and agents? It's w... New releases from Microsoft Research, live in 1 hour. Join for ai that runs your repo + verificati... Introducing GridSFM, a small foundation model that can predict AC optimal power flow in milliseconds... MatterSim is expanding what AI can do for materials science—from faster large-scale simulations to M... Using SocialReasoning Bench, we observed a stable pattern across models—agents execute competently, ... Tyger moves the most demanding MRI processing to the cloud, helping researchers turn raw signals int... Designing AI isn’t just about performance. It’s about tradeoffs that affect people and the planet. I... Microsoft researchers share advances in building and operating large-scale distributed systems, span... Research Focus: AI agents leaking enterprise data, a smarter OS for cloud deployment, and new resear... Safe agents don’t guarantee a safe ecosystem of interconnected agents. Microsoft Research examines w... Coming May 14 at Microsoft Research Forum: a new release and demo from MSR AI Frontiers. Plus new ... Coming May 14 at Microsoft Research Forum: a new release and demo from MSR AI Frontiers. Plus new ... Congratulations to Philippe Laban, Jennifer Neville, and collaborators on their Best Paper Award at ... AutoAdapt automates the design and tuning of domain adaptation workflows for large language models. ...

AI agents can't remember past conversations. They must constantly reload or retrieve context, which ...

Microsoft Re · 2026-06-30 · via Microsoft Research(@MSFTResearch)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。