Why Agentic Inference Needs Prefix-Aware Routing Infrastructure
In the second of a three-part series on agentic AI, learn how prefix caching and cache-aware routing reduce time-to-first-token for agentic inference.
CoreWeave Blog6 min read
Agent Workflows
241 stories
Your Agent Is Only as Good as Your Infrastructure
The first of a three-part series on agentic AI. Production AI agents depend on more than model quality. Learn how multi-turn tool calls, bursty demand, and infrastructure shape performance.
CoreWeave Blog5 min read
How one squad at Sonar reviews AI-generated code: A look at our agentic workflow
Learn how one Sonar squad built a three-layer review process for AI-generated code, SonarQube analysis, Gitar, then a human reviewer. Read the case study.
Gitar Blog6 min read
Gemini 4 Argon's Million-Token Output, Explained
Gemini 4 Argon can output a million tokens in one response. Here's why that ceiling matters for test-time compute and long agent runs.
MindStudio Blog7 min read
Build agent memory with NVIDIA NeMo Agent Toolkit and Amazon S3 Vectors
Learn how to use Amazon S3 Vectors as the persistent memory layer within the NVIDIA NeMo Agent Toolkit (NAT), deployed on Amazon Elastic Kubernetes Service (Amazon EKS).
AWS ML Blog14 min read
Clef: Open-source decision models, and new RL fine-tuning platform
Article URL: https://blog.cloudflare.com/clef-decision-models/ Comments URL: https://news.ycombinator.com/item?id=49923692 Points: 218 # Comments: 78
Hacker News11 min read
AWS debuts Strands Decider 2B, a first lightweight decision model for accelerate agentic workflows
Amazon Web Services Inc.’s Strands Labs team has been playing around with an emerging class of lightweight artificial intelligence systems known as “decision models,” and it’s now making the fruits of that work available to the open-source community.
SiliconANGLE4 min read
From vulnerability alert to verified patch: an agent workflow
Give a coding agent a bounded dependency patch with explicit compatibility checks and review requirements.
Hoplite Blog4 min read57% of Shoppers Will Let AI Agents Switch Brands. Here’s How AI Actually Decides Which Brand to Pick.
A survey of US shoppers in 2026 found that 57% would let an AI agent switch brands if it found better value. More than half — 51% — said they’d let AI handle the entire purchase process from research to checkout.
LLMagnet Blog9 min readMoFlow: Multi-Objective Agentic Workflow Generation
We study the generation of agentic workflows that jointly optimize multiple objectives, such as accuracy, cost, latency, robustness, and consistency. Existing methods for workflow generation typically optimize accuracy alone or a weighted sum of objectives, so each trained generator commits to one…
arXiv - cs.AI2 min read
DigitalOcean MicroVMs: the Compute foundation for building your AI agent infrastructure (private preview)
Build your own agent platform on DigitalOcean MicroVMs: isolated Firecracker VMs that pause when idle and resume with state intact. Now in private preview.
DigitalOcean Blog5 min read
AI Agent Orchestration: Patterns, How It Works, and Build vs Buy
AI agent orchestration explained: the coordination patterns, how it works at production scale, and when to build on a framework versus buy a platform.
Voiceflow Blog9 min readCalifornia’s AI Kill Switch Needs More Than an Off Button
Stopping the model is only the beginning. The real test is whether everything it set in motion stops with it.
Towards AI7 min read
Cohere’s faster query model barely dents retrieval quality in its tests
Cohere released Embed 5 on Wednesday, giving teams the option to index data with Embed 5 Pro and query those The post Cohere’s faster query model barely dents retrieval quality in its tests appeared first on The New Stack.
The New Stack - AI4 min read
Saga Pattern: Agile Recovery for AI Agents in 2026
How the saga pattern helps AI agent recovery in multi-step workflows Your AI agent got three steps right, then failed on the fourth. The order exists, the card may be charged, the customer might already have an email, and the CRM is now out of sync.
Dev.to AI12 min read
From Upstream Changes to Downstream Confidence: Inside Torch Spyre’s Integration with PyTorch CRCR
TL;DR PyTorch’s Cross-Repository CI Relay (CRCR) gives out-of-tree accelerators a clean, scalable way to plug into upstream CI – and it leaves each backend free to decide which of PyTorch’s...
PyTorch Blog15 min readWe upgraded the AI models to GPT-6 Sol
We’ve upgraded the AI models used across Instafill.ai to GPT-6 Sol, the latest Sol model in OpenAI’s GPT-6 family. The upgrade is already live across every Instafill.ai account, and there’s nothing you need to change on your side.
Instafill.ai Blog4 min read
Give your LangGraph agent real-time web data with Apify
Connect a LangGraph agent to Apify through the official langchain-apify integration or Apify MCP Server, and give it real-time web search, scraping, and social media data.
Apify Blog13 min read
Showing 72 of 241 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts