Building AI agents that work well in a demo is one thing, but running them in production requires serious infrastructure. At Google Cloud Next ’26, we introduced Gemini Enterprise Agent Platform to help developers build, deploy, scale, govern, and optimize autonomous AI agents. From managing long-running state and enforcing security with the Agent Governance Stack, …
Multi-tool-integrated reasoning enables LLM-empowered tool-use agents to solve complex tasks by interleaving natural-language reasoning with calls to external tools. However, training such agents using outcome-only rewards suffers from credit-assignment ambiguity, obscuring which intermediate steps (or tool-use decisions) lead to success or failure. In this paper, we propose PORTool, an importance-aware policy-optimization algorithm that reinforces agents’ …
Saish Sali, Nipun Kumar, Sura Elamurugu Introduction As Netflix has grown, machine learning continues to support our ability to deliver value to members and drive excellence across multiple areas of our business. When Netflix began investing in machine learning over a decade ago, it was primarily focused on a single domain: personalization. Scala was the …
Read more “Democratizing Machine Learning at Netflix: Building the Model Lifecycle Graph”
Business leaders across industries rely on operational dashboards as the shared source of truth that their teams execute against daily. But dashboards are built to answer known questions. When teams need to explore further, ad-hoc, multi-dimensional, or unforeseen questions, they hit a bottleneck. They wait hours or days for BI teams to build new views …
This paper was accepted at the Fifth Workshop on Natural Language Generation, Evaluation, and Metrics at ACL 2026. Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the active execution loop, such assessments identify errors that are usually addressed through prompt-tuning or retraining, …
Read more “Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents”
By Nipun Kumar, Rajat Shah, Peter Chng Introduction This is the first blog post in a multi-part series that shares technical insights into how our ML model serving infrastructure powers several personalized experiences at scale across various domains (e.g., title recommendations, commerce). In this introductory blog post, we will dive into our domain-independent API abstraction and …
Migrating to Amazon Quick doesn’t have to mean starting from scratch. Your dashboards encode hard-won domain knowledge: calculated fields your analysts perfected, layouts your executives rely on every Monday morning, security rules tuned to your org chart. You want AI-powered insights and serverless scale, but you’re staring at hundreds of dashboards and a migration estimate …
Read more “AWS Transform now automates BI migration to Amazon Quick in days”
Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are substantially higher, state-of-the-art systems almost exclusively rely on diffusion-based models. In this work, we revisit this design space by presenting …
Read more “STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows”
The National Health Service (NHS) has delivered universal healthcare to an entire nation for over 75 years. With 1.5 million staff providing care to approximately 57 million patients across hundreds of hospital trusts — using decades old legacy infrastructure — the NHS is one of the most operationally complex organisations on earth. For most of its history, the NHS has …
Read more “Ready, Set, Build with the NHS Federated Data Platform”
Large language models (LLMs) now drive the most advanced conversational agents, creative tools, and decision-support systems. However, their raw output often contains inaccuracies, policy misalignments, or unhelpful phrasing—issues that undermine trust and limit real-world utility. Reinforcement Fine‑Tuning (RFT) has emerged as the preferred method to align these models efficiently, using automated reward signals to replace …