8537 articles tagged with Agents
Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training distributions. We introduce ...
Pharma’s next security problem isn’t the code. It’s what the AI agent can touch. Nicole. Raleigh Tue, 13/10/2026 - 12:13
AI 跨境电商运营智能体工具箱 · 把运营 SOP 拆成 7 个可复用的 AI Agent 工作流，含 Prompt、模板与真实案例
A Journalist Got Meta's Muse AI Agent to Sext - Meta Says That's Finehttps://www.wired.com/story/i-got-my-muse-ai-agent-to-sext-me-and-meta-says-thats-totally-fine/#mix #ai #meta
"A practical architecture for AI agents that handle e-commerce refunds, with scoped tools, meaningful...
A Wired reporter tested Meta's Muse AI agent and found it willing to generate explicit sexual content. Meta defended the behavior as legal adult interaction. #mix #ai #metahttps://...
The word “agent” is being attached to almost every AI feature right now. A prompt calls a model, the...
Give an AI agent a real toolset (25, 40, more) and every call pays for it. The agent reads every tool...
What The Function: your AI agent decompiles games you own into C that compiles to the exact same bytes. Runs locally.
APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation
ReliaQuest details an AI agent attack that used one exposed endpoint and the Cairn platform to achieve a full server takeover in under 24 hours.#AIAgents #AIAgentAttack #ServerTake...
GLM-Legal: Advancing Agentic Legal IntelligenceArticle URL: https://z.ai/blog/glm-legal Comments URL: https://news.ycombinator.com/item?id=50058507 Points: 9 # Comments: 0https://z...
An $800 voice agent cost a healthcare founder $50,000. I heard this directly from him last week. The...
RT @tomshardware: AMD stellt das Helion-Referenzdesign für agentic AI-Server vor, mit bis zu 32.768 Zen-6-Kernen „Venice“ — das Rack-Design wird nächstes Jahr in CPU-only- und All-...
TestMu AI、2026年Gartner（R）Magic Quadrant（TM）エージェント型ソフトウェア品質保証プラットフォーム（Agentic Software Quality Assurance Platforms）部門でリーダーに位置づけられる https://www.yayafa.com/?p=2909377 #AgenticAi #AI #...
Which AI agent framework to pick in 2026: release history, production failures and real costs for LangGraph, CrewAI and AutoGen.
The most dangerous part of this attack is not the stealing. It is the trap that fires when you do the...
AMD has introduced Helion, an open rack architecture for agentic AI workloads.Source: DigiTimes Asiahttps://www.digitimes.com/news/a20261013PD214/amd-design-cooling-infrastructure-...
I Asked Muse to Help Me Book My Holiday Travel. It Didn’t Fly Far.Meta is pushing its AI agent as a round-the-clock personal assistants, but it still gets hung up on some basic tas...
City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large outdoor scenes. We propose Urbex...
Long-horizon agents have drawn growing attention for their ability to work autonomously -- from hours to days -- on economically valuable tasks, a capability essential to automated...
Test-time scaling for large language models (LLMs) can involve generating multiple candidate solutions for selection or revising an earlier attempt. To guide selection and revision...
Long-horizon, semi-verifiable agentic tasks often rely on rubric-based evaluation, but the evidence needed to assess these tasks can be spread across the environment state and the ...
openKylin: The AI Agent Linux Desktop https://techstrong.ai/articles/openkylin-the-ai-agent-linux-desktop/ via @techstrongai & @sjvnSome #Linux distros are steering clear of #AI. C...