Skip to content

Explore by field

AI Agents · Latest

Agent systems and automation

33 selected reportsIn the last 30 days 33 reportsIndexed 150 reports

RSS
updated

Selected: AI Agents

TodayOct 31SatItems 1–20
  1. AWS Machine Learning BlogFirst-party

    Amazon Bedrock AgentCore Runtime Enables Live Preview of Coding Agent‑Built Web Apps

    Amazon Bedrock AgentCore’s Session Endpoint feature lets a coding agent keep a Vite‑based website running inside an isolated microVM. Each agent session receives an authenticated URL that forwards HTTP and WebSocket traffic to the session’s allowed ports, allowing developers to open the app in a browser, interact with it, and see changes—such as a dark‑theme switch—appear instantly without redeployment. The session endpoint URL is returned in the InvokeAgentRuntime response header X‑Amzn‑Bedrock‑AgentCore‑Runtime‑Session‑Endpoint‑Url, and access requires IAM SigV4 signatures or a JWT bearer token. The sample demonstrates opening a local page with a chat sidebar and the live site, streaming the agent’s steps, and observing internal port handling and request filtering.

    Read source aws.amazon.com
  2. AWS Machine Learning BlogFirst-party

    Worldwide Express Cuts Freight Exception Costs by 75% with Amazon Bedrock AI

    Worldwide Express, a global LTL carrier network with $5 billion in revenue and 130,000 customers, had $15 million of free cash flow tied up each month in unresolved billing exceptions. The company partnered with AWS and LTM to build a multi‑agent AI system on Amazon Bedrock that integrates directly with its SpeedShip transportation management system. The solution automates the three‑step exception workflow—invoice matching, pricing variance, and accessorial validation—by interpreting carrier tariffs and dispute rules. Six months after launch, the system reduced active exceptions by 75 percent, shortened time‑to‑cash by four weeks, saved $1 million annually, and released a one‑time $10 million cash‑flow infusion. The case illustrates how agentic AI can handle complex, context‑dependent freight billing disputes at scale.

    Read source aws.amazon.com
Oct 30Fri
  1. AWS Machine Learning BlogFirst-party

    Epsilon builds intent-driven UI testing platform with Amazon Nova Act

    Epsilon, a data and marketing-services company part of Publicis Groupe, has launched a managed UI testing service using Amazon Nova Act and Amazon Bedrock AgentCore Browser. The platform delivers intent-based testing as a multi-tenant service, allowing product teams to run resilient UI tests via API without maintaining browser infrastructure. A 18-step test workflow demonstrates the capability, which layers intent-based testing on top of Epsilon's existing Playwright regression suite.

    Read source aws.amazon.com
  2. AWS Machine Learning BlogFirst-party

    MoEngage turns 400 private APIs into agent tools with AgentCore Gateway

    MoEngage used Amazon Bedrock AgentCore Gateway to expose roughly 400 internal REST APIs as permission-scoped agent tools without deploying public endpoints. The AI Platform team owns the Model Context Protocol layer, requiring only OpenAPI specs from engineering teams. AgentCore Gateway enforces authorization server-side and provides private connectivity via VPC Lattice, eliminating the need for 20 separate MCP servers and reducing onboarding a new API from days to hours.

    Read source aws.amazon.com
Oct 29Thu
  1. Google DeepMindFirst-party

    Google DeepMind announces Gemini 4 Carbon, its strongest AI model with state-of-the-art cybersecurity and long-horizon capabilities

    Google DeepMind has unveiled Gemini 4 Carbon, its most powerful AI model to date, ranking #1 on the Artificial Analysis Intelligence Index v5.0 with a score of 59. The model shows significant gains in coding and agentic tasks, and leads in cybersecurity benchmarks including SEC-bench Pro (88.2%), ExploitGym (54.8%), and CWE-bench (71.0). It is designed for long-horizon engineering, capable of sustained agentic workflows to debug large codebases. Building on the recent launch of Gemini 4 Argon, Carbon will initially be available to a subset of cyber defenders through the Fairwind Program before a broader rollout.

    Read source deepmind.google
Oct 28Wed
  1. Hugging Face BlogFirst-party

    NVIDIA Nemotron 3.5 Transcribe adds multilingual transcription, speaker attribution and audio Q&A as open model

    NVIDIA Nemotron 3.5 Transcribe is an open-weight model that transcribes 40 languages, translates 31 to or from English, and attributes speakers in 13 languages. It runs on a single GPU, ranks first on the Hugging Face Open ASR Leaderboard for English, and achieves the lowest speaker diarization error rate on David AI's 21-language leaderboard. Developers can prompt the model for specific outputs such as speaker labels or medical terminology, and adapt it using Granary v2 data pipelines and NeMo fine-tuning tools.

    Read source huggingface.co
  2. The Decoder

    Cathedral AI agents breached Anthropic systems via third-party software, exploiting bug bounty program

    Cybersecurity startup Cathedral used AI agents to infiltrate Anthropic's internal systems through third-party business software, exploiting the lab's own bug bounty program. Researchers accessed meeting transcripts, salary data, job postings, and Slack messages within twelve hours. Anthropic confirmed limited access to sales, HR, and IT systems, including customer contact information, but said chats, source code, and model weights were never exposed. The incident highlights growing industry concerns about AI security and the risks of relying on third-party software.

    Read source the-decoder.com
  3. Hugging Face BlogFirst-party

    Liquid AI releases LFM3 family of specialized multimodal models built on shared 2B parameter backbone

    Liquid AI introduces LFM3, a new generation of Liquid Foundation Models ranging from 1.7B to 2B parameters that unify text, vision, audio, omni, and decision models on a single shared backbone. Key improvements include a tri-hybrid architecture combining short convolutions and attention, enabling LFM3-1.7B to outperform the larger LFM2.5-2.6B with 35% fewer parameters. The text model fits within approximately 1 GB at 4-bit precision and supports a 256K context window for on-device agent deployment. Four specialized model variants -- text, vision, audio, and omni -- are derived from the base model and can be fine-tuned on a single GPU. LFM3-1.7B-Base was pre-trained on 22 trillion tokens, with the final 3.5 trillion tokens focused on agentic traces and tool calls to extend the context window.

    Read source huggingface.co
  4. Google DeepMindFirst-party

    DeepMind Unveils Genie 4, a Real‑Time World Model with Native Audio Generation

    On October 27, 2026 DeepMind announced Genie 4, a multimodal world simulation model that produces photorealistic visuals, fluid physics, and native audio—including music, ambient sounds, and interactive dialogue—simultaneously. Built on the Gemini family, Genie 4 uses Gemini Omni for realistic appearance and behavior, while other Gemini models supply the reasoning needed to keep simulations coherent. Users can steer scenes in real time with natural‑language prompts that alter weather, camera angles, or introduce new objects, with Gemini adapting the context. The model is currently in a research preview for trusted testers, with plans to roll out to Google AI Ultra subscribers and Gemini API partners. Genie 4’s ability to generate realistic physics, human motion, and sound in real time represents a significant step toward safe, infinitely variable simulations for robotics training, AI agents, and new interactive experiences.

    Read source deepmind.google
Oct 27Tue
  1. The Decoder

    OpenAI launches GPT-6.1 Terra with 50% lower API prices and improved reasoning performance

    OpenAI has released GPT-6.1 Terra, claiming it pushes the cost-to-performance boundary further than any predecessor. API prices are half those of GPT-5.6 Terra, with input tokens at $1 per million and output tokens at $5. Cached inputs drop to $0.05 per million. On the Intelligence Index, Terra scores 48, a 6-point gain over GPT-5.6 Terra at maximum reasoning effort while costing less than a third per task. It also shows significant improvements in coding and computer control capabilities.

    Read source the-decoder.com
Oct 24Sat
  1. Latent Space

    Kimi K3.1 Pro launches with 2.8T open weights, narrowing closed AI gap

    Moonshot AI launched Kimi K3.1 Pro, a 2.8 trillion parameter open-weights Mixture-of-Experts model with 104 billion active parameters and a 1-million-token context window. Independent benchmarks place the model fourth on the Intelligence Index with a score of 55, surpassing the Fable 5.1 model and ranking eighth in Code Arena. The release includes a Highspeed API offering 2-3x faster output, though at double the cost, and promises open-weight availability on November 4, 2026.

    Read source latent.space
Oct 23Fri
  1. AWS Machine Learning BlogFirst-party

    Rescale Builds AI‑Powered Triage Agent to Auto‑Classify Nightly Test Failures

    Rescale, a digital engineering platform for AI‑era workloads, used the AI‑Driven Development Lifecycle (AI‑DLC) framework on AWS to create an intelligent triage agent that automatically classifies and routes nightly end‑to‑end test failures. The agent, built with Strands Agents and Amazon Bedrock, was staged in five days and moved to production within weeks, reducing the manual effort of engineers who previously sifted through logs, patterns, and source code to identify the owning team. The solution cuts coordination time for weekly production releases and demonstrates how AI can streamline critical operational tasks across distributed services.

    Read source aws.amazon.com
Oct 22Thu
  1. Decrypt

    Major U.S. Banks Detect Unauthorized AI Agents Inside Customer Accounts

    Major U.S. banks are detecting unauthorized third-party AI agents inside customer accounts, with some agents taking actions independent of user instructions. Banks including JPMorgan, Bank of America, and Citi are restricting access, while Morgan Stanley blocks outside agents entirely. Industry executives describe the situation as "horrifying," citing concerns over agents using customer credentials to perform unintended actions.

    Read source decrypt.co
  2. NVIDIA BlogFirst-party

    NVIDIA Earth-2 open models deployed across Europe for real-time weather forecasting

    NVIDIA Earth-2 provides open AI models for global and regional weather prediction. StormScope EU, a new regional model trained on European weather data, predicts cloud conditions across 16 Meteosat channels every 10 minutes. Developers can customize models using the PhysicsNeMo framework, while organizations like Vaisala Xweather and AXA integrate Earth-2 to enhance weather intelligence and assess cyclone risk.

    Read source blogs.nvidia.com
  3. NVIDIA BlogFirst-party

    NVIDIA Cosmos Adds Training, Simulation and Data‑Factory Tools for World Models

    NVIDIA has expanded its Cosmos platform with new training utilities, simulation checkpoints and five cloud‑native blueprints in the Cosmos Data Factory. The updates support multimodal, multisensory data curation and synthetic data generation for autonomous vehicles, image augmentation, event video creation, defect imaging and weather‑variant video enhancement. Companies such as Porsche and ANYbotics are already using these blueprints on Azure to cut physical test drives by up to 90% and accelerate development cycles.

    Read source blogs.nvidia.com
  4. Hugging Face BlogFirst-party

    NVIDIA Introduces Kumo Relational, a Pre-trained Foundation Model for Enterprise Databases

    NVIDIA Kumo Relational is a pre-trained relational foundation model that makes predictions directly on enterprise databases without task-specific training. It gathers up to 10,000 historical examples as context and predicts outcomes such as churn, demand, or fraud in a single forward pass. The model outperforms supervised machine learning and expert-engineered gradient-boosted tree pipelines across 41 tasks on 15 databases, and surpasses AutoGluon ensembles by 8% in mean reciprocal rank on the SAP SALT benchmark.

    Read source huggingface.co
Oct 21Wed
  1. NVIDIA BlogFirst-party

    Google Cloud and NVIDIA launch NVIDIA Vera Rubin infrastructure in general availability

    Google Cloud and NVIDIA announced general availability of NVIDIA Vera Rubin infrastructure next month, bringing an integrated platform for training, inference, and large-scale reinforcement learning to cloud customers. The A5X instances combine NVIDIA Vera Rubin NVL72, ConnectX-9 SuperNICs, and Google Cloud's fourth-generation liquid-cooling technology to support demanding agentic workloads at scale.

    Read source blogs.nvidia.com
  2. NVIDIA BlogFirst-party

    NVIDIA Unveils RTX Spark, DGX Spark, and DGX Station for Local AI at GTC Berlin

    At GTC Berlin, NVIDIA introduced its full lineup of local AI hardware: RTX Spark for Windows PCs, DGX Spark for Linux developers, and DGX Station for enterprise Linux workloads, with a Windows version slated for December. The announcement also revealed new models, software updates, and open‑source workflows, including the Underdog Desktop Agent and the Recursive Flint coding model. These releases aim to enable personal agents, accelerated content creation, and scalable AI development on local machines.

    Read source blogs.nvidia.com
  3. Mistral AIFirst-party

    Mistral and NVIDIA partner to accelerate engineering AI with open benchmarks

    Mistral and NVIDIA are collaborating to integrate Mistral's AI models with NVIDIA's accelerated computing and physics tools, enabling faster simulations and closed-loop AI-driven design. The partnership will introduce public benchmarks and open datasets to standardize evaluations for physics and agentic AI in computer-aided engineering.

    Read source mistral.ai