Knowledge catalogue
The easiest way to deploy your agent. One command, instant deployment: `deepagents deploy` 🚀Deep Agents deploy Today we’re launching Deep Agents deploy in beta. Deep Agents deploy is the fastest way t
Building agents locally does not mean they’re ready to deploy in production LangSmith deployments helps with that 🔐 One deployment, isolated data per user. Add custom auth so every user gets their own
We're excited to announce the launch of Amazon SageMaker JumpStart optimized deployments. SageMaker JumpStart improved deployments address the need for rich and straightforward deployment customizatio
Introducing the OpenAI Deployment Company, which will help businesses maximally succeed with their deployments of AI. Starting with 150 Forward Deployed Engineers and Deployment Specialists, and $4 bi
OpenAI announced the acquisition of Tomoro, a company that will add 150 experienced Forward Deployed Engineers and Deployment Specialists to OpenAI's team. This acquisition appears focused on expandin
Today we’re launching the OpenAI Deployment Company to help businesses build and deploy AI. It's majority-owned and controlled by OpenAI. It brings together 19 leading investment firms, consultancies,
Reuters: OpenAI launches the OpenAI Deployment Company with a 4B+ investment to help organizations build and deploy AI systems, and acquires AI consulting firm Tomoro — OpenAI said on Monday it is set
🔒`deepagents deploy` now supports custom auth: turn a single deployment into a multi-tenant platform. per-user resource and thread isolation, access control, and your own auth provider, all without sp
arXiv:2605.27827v1 Announce Type: new Abstract: AI governance frameworks increasingly emphasize fairness, transparency, accountability, and lifecycle risk management in high-stakes domains. However, m
arXiv:2605.28097v1 Announce Type: new Abstract: Canary deployment routes a fraction of traffic to a new software version, monitors metrics, and rolls back on regression. Mainstream controllers (Argo R
Deploying a Hermes Agent with Fly, Modal, OpenRouter, & Cloudflare 02:43 Managed vs VPS 06:08 Architecture 15:14 Setup 22:23 Deployment 28:00 Access / OIDC 39:57 Hermes and Open WebUI 52:07 Cloudflare
arXiv:2605.27720v1 Announce Type: new Abstract: Reinforcement learning and data-driven autonomous controllers are commonly evaluated using cumulative reward and empirical success frequency under finit
Vercel has updated its deployment retention policies to automatically preserve active branch deployments, preventing them from being deleted even when retention limits are reached. This feature ensure
arXiv:2604.14661v1 Announce Type: cross Abstract: Edge AI model deployment is a multi-stage engineering process involving model conversion, operator compatibility handling, quantization calibration, r
This post discusses the LangSmith UI dashboard that becomes available after deploying a project, which provides visualization and tracking capabilities for monitoring deployments. The dashboard allows
1. We believe in iterative deployment; although GPT-5.5 is already a smart model, we expect rapid improvements. Iterative deployment is a big part of our safety strategy; we believe the world will be
arXiv:2607.07184v1 Announce Type: cross Abstract: Pre-deployment safety evaluations aim to inform the downstream risks of releasing a new AI model. Yet most evaluations provide limited evidence about
arXiv:2607.22697v1 Announce Type: new Abstract: Deployed AI systems are often trained from broad candidate data pools, necessitating data curation towards the deployment test distribution. However, st
arXiv:2607.22708v1 Announce Type: new Abstract: Deploying a vision-language model with full UI understanding on end devices has long been trapped between accuracy and efficiency: on one side is the ac
Across 101 enterprises, agent orchestration is consolidating onto model-provider platforms — Anthropic’s Claude leads by a wide margin — chosen for the gravity of the underlying model and judged on re
arXiv:2608.04502v1 Announce Type: cross Abstract: Attention--Feed-Forward Network (FFN) Disaggregation (AFD) is emerging as a promising architecture for serving Mixture-of-Experts (MoE) language model
Vercel introduced a trusted sources feature for deployment protection that allows teams to control which sources can trigger deployments, enhancing security by restricting deployment access to verifie
arXiv:2506.09044v2 Announce Type: replace Abstract: Machine Learning systems are increasingly deployed in decision-making settings that shape user behavior and, in turn, the data on which future decis
arXiv:2610.07276v1 Announce Type: cross Abstract: Deployment-time safety of language models is commonly implemented through runtime guardrails such as input moderation, routing, retrieval verification
arXiv:2609.12412v1 Announce Type: cross Abstract: Foundation models, including large language models, vision-language models, and time-series foundation models, are increasingly deployed on embedded a
arXiv:2609.11954v1 Announce Type: new Abstract: As deep learning models are increasingly deployed on resource constrained devices, the demand for efficient model optimization techniques continues to g
arXiv:2609.02095v1 Announce Type: new Abstract: An AI agent can perform well on benchmarks and still be unsuitable for deployment. Existing AI-agent benchmarks measure whether an agent can complete re
arXiv:2607.10103v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become widely deployed, their outputs can be copied, transformed, and redistributed at scale without reliable
arXiv:2609.02302v1 Announce Type: new Abstract: A core obstacle to alignment evaluation is evaluation awareness: capable models can tell when they are being tested rather than deployed, weakening the
arXiv:2608.26235v1 Announce Type: new Abstract: Accuracy-only benchmarking of reasoning-capable large language models misses a central deployment question: when do extended thinking tokens earn their
Vercel announced a redesign of its Deployments List interface to improve visibility and management of project deployments. The update likely enhances the user interface for viewing deployment history,
arXiv:2605.25997v1 Announce Type: new Abstract: Benchmarks increasingly guide deployment, procurement and scientific screening, yet a score supports only the response it records, not necessarily the d
arXiv:2604.23058v1 Announce Type: cross Abstract: Firms are deploying more capable AI systems, but organizational controls often have not kept pace. These systems can generate greater productivity gai
Native Deployment Checks can now be run on every Vercel deployment, processing linting and typechecking in parallel with the build process. These built-in checks integrate with existing integrations (
arXiv:2511.17902v3 Announce Type: replace-cross Abstract: Distributed Fiber Optic Sensing (DFOS) is promising for long-range perimeter security, yet practical deployment faces three key obstacles: sev
Vercel has updated its default deployment retention policy for hobby tier projects to automatically retain deployments for 30 days. This change simplifies deployment management for free-tier users by
arXiv:2608.14599v1 Announce Type: cross Abstract: The placement of base station (BS) is a fundamental determinant of coverage and capacity of urban wireless networks. Yet large-scale BS deployment opt
arXiv:2608.16411v1 Announce Type: cross Abstract: LLM-based agents are rapidly moving from research prototypes into the core business processes of organizations, but these agents pose deployment risks
arXiv:2606.07586v1 Announce Type: cross Abstract: Spatial neural processing units (NPUs) provide an energy-efficient platform for edge LLM inference, but efficiently deploying an LLM end-to-end on suc
arXiv:2605.18059v1 Announce Type: new Abstract: Robustness is a critical requirement for deploying autonomous driving systems in the real world. Existing robustness benchmarks for autonomous driving h
Building and serving models on infrastructure is a strong use case for businesses. In Google Cloud, you have the ability to design your AI infrastructure to suit your workloads. Recently, I experiment
arXiv:2609.14592v1 Announce Type: new Abstract: Artificial intelligence systems are rapidly becoming critical components in healthcare, finance, public services, and other safety-critical domains. Yet
arXiv:2609.13785v1 Announce Type: new Abstract: Oracle-style quantities, including virtual best solvers, selected-portfolio VBS, virtual-best encodings, and best-in-family summaries, are widely report
arXiv:2609.10550v1 Announce Type: cross Abstract: AI deployment performance is shaped not by model architecture alone, but by interactions among compression, compiler transformations, and serving poli
arXiv:2607.09835v2 Announce Type: replace Abstract: The recently introduced YOLO26 architecture incorporates NMS-free end-to-end inference and is optimized for deployment on resource-constrained CPU-b
arXiv:2608.20513v1 Announce Type: cross Abstract: Continuous deployment to large scale production systems creates a tension between release velocity and reliability. Every change is a potential reliab
arXiv:2608.10506v1 Announce Type: cross Abstract: Accurate pre-deployment estimation of CNN inference cost--energy, latency, and peak memory--is increasingly critical as models are deployed on resourc
Vercel CLI now supports dry-run deployments, allowing developers to preview and test deployment configurations without actually publishing changes to production or staging environments. This feature h
The financial services industry (FSI) operates under a unique set of non-negotiable requirements: the need for strict regulatory compliance, sub-millisecond transactional speeds, and security that ver
arXiv:2606.27688v1 Announce Type: cross Abstract: In financial forecasting, predictive performance depends not only on which model is trained, but also on how the trained model is deployed. We study t
arXiv:2606.24996v1 Announce Type: new Abstract: Forecasting leaderboards rank models by predictive quality, but their winners are often read as deployment-ready top-1 advice. That reading can fail whe
arXiv:2603.22126v3 Announce Type: replace Abstract: Deploying learned robot manipulation policies in industrial settings requires rigorous pre-deployment validation, yet exhaustive testing across high
arXiv:2609.27571v1 Announce Type: cross Abstract: Deployment requires an agent to turn application code into a running system whose services connect, become ready, and remain observable. FDE-Bench eva
🌐 Supporting open source. Expanding deployment options. We’ll work closely with the open-source community on V4.1-Flash inference support and explore more deployment options. Planning a large-scale de
arXiv:2608.03511v1 Announce Type: cross Abstract: Active learning (AL) promises to reduce the cost of medical imaging projects by lowering the number of clinical labels required. However, practical de
arXiv:2607.21403v1 Announce Type: new Abstract: Mobile-health interventions increasingly use online learning and decision making algorithms to personalize when to nudge users toward healthier behavior
arXiv:2606.20629v1 Announce Type: cross Abstract: LLM agents are increasingly deployed as multi-role teams, where tasks are divided across specialized roles such as planner, executor, and verifier. In
as agents run for longer and with more context, there's a lot of tricky things you have to consider for deployment! super excited to dive into deploying Deep Agents for this Boston tech week meetup! .
arXiv:2605.05009v1 Announce Type: new Abstract: Many decentralized distillation methods are designed around training-time coordination, yet deploy each node in isolation even when more capable neighbo
arXiv:2604.28056v1 Announce Type: new Abstract: Large language models (LLMs) make reward design in reinforcement learning substantially more scalable, but generated rewards are not automatically relia