Google DeepMind introduces Gemini 4 Hydrogen
Google DeepMind News - deepmind.google · 2026-11-12
In September 2024, we launched Replit Agent , the first generally available coding agent that enabled anyone to build software by describing it in their own words
Replit - replit.com · 2026-11-12
An open-source AI coding agent that lives in your terminal. - Release Qwen Code Desktop v0.27.3 · QwenLM/qwen-code
Qwen Code Releases - github.com · 2026-11-13
Orchestrator takes a dynamic, bidirectional approach between Carbon and Gemini 4 Hydrogen within the evolution of a single trajectory. For example
Reference discovery - antigravity.google · 2026-11-12
Decision models answer a question with a typed output, such as a choice among options with a probability for each, so one model can choose an agent's actions, evaluate actions already taken, or score every action to teach a policy with reinforcement learning.
arXiv Language-Model Research - arxiv.org · 2026-11-12
To address this, we developed LLMON (LLM Object Notation, pronounced "lemon"), an LLM-native markup language for explicitly communicating structure and semantics to the models
Reference discovery - huggingface.co · 2026-11-12
Model architecture shapes the scaling behavior, training efficiency, and inference cost of LLMs, making it a central focus of both industry and academia.
arXiv Language-Model Research - arxiv.org · 2026-11-12
Large language model (LLM) agents use external skills to reuse task procedures and experience with tools.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
Tool-using language-model agents accumulate histories of their own mistakes, and a system that compacts
arXiv coding-agent research feed - arxiv.org · 2026-11-13
In this post, we build an internal assistant for AnyCompany. All employees share the same agent and knowledge base
AWS Machine Learning Blog - aws.amazon.com · 2026-11-12
Over the past year, AI agents have moved from exploration into engineering. Enterprise teams are shipping large language model (LLM) systems that call tools, orchestrate APIs
AWS Machine Learning Blog - aws.amazon.com · 2026-11-12
Get per identity Amazon Bedrock cost visibility and enforceable spend limits using only AWS native features, with no application code for the common case.
AWS Machine Learning Blog - aws.amazon.com · 2026-11-12
Most AI assistants respond only when prompted, remaining silent even when events in the video stream offer meaningful opportunities for conversation.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
Comparing per token prices hides the real cost of running a model on Amazon Bedrock.
AWS Machine Learning Blog - aws.amazon.com · 2026-11-12
We introduce GeoWorld, a controllable and continuously evolving geographic environment platform for LLM agents, and LiveGeo, a benchmark for evaluating reliable decision making in real world geographic environments using GeoWorld.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
Program evolution provides a promising approach to discover agent memory designs and study the choices underlying their effectiveness.
arXiv Language-Model Research - arxiv.org · 2026-11-12
Multi agent deep research systems use delegation to parallelize search and keep long tool traces out of the main agent's context.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
Combining vision language models (VLMs) with parameter efficient fine tuning (PEFT) offers a promising approach to few shot whole slide image (WSI) classification in computational pathology.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
Enforcement defenses against prompt injection, such as CaMeL, Progent, IPIGuard and DRIFT, ask the agent's own model to write a security artifact (a program, a privilege policy, a dependency graph or a constraint list) that code then enforces.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
Today's AI workloads are rapidly changing: new models are released more often, model architectures are increasingly diverse
arXiv coding-agent research feed - arxiv.org · 2026-11-13
Applying machine learning systems to new domains introduces bottlenecks in both labeled data acquisition and manual pipeline engineering.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
When we judge that our reasoning was defective, it seems plausible that we should abandon the conclusion it produced
arXiv coding-agent research feed - arxiv.org · 2026-11-13
Remotion came out in 2021, way before agents were the hype
Remotion Documentation - www.remotion.dev · 2026-11-12
Build a self service LLM gateway with LiteLLM on AWS Fargate that puts Amazon Bedrock foundation models behind an OpenAI compatible API.
AWS Machine Learning Blog - aws.amazon.com · 2026-11-12
On device inference requires kernels that make effective use of local accelerators.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
Current benchmarks for LLM-driven data agents saturate quickly and cannot target specific capabilities. We present SynthCorp
arXiv coding-agent research feed - arxiv.org · 2026-11-13
The migration guide in the amazon bedrock skill helps you migrate a customer managed Amazon Bedrock knowledge base to a Managed Knowledge Base.
AWS Machine Learning Blog - aws.amazon.com · 2026-11-12
AI agents now run multi step workloads for hours and act on behalf of users, raising the bar for secure, scalable agent compute.
AWS Machine Learning Blog - aws.amazon.com · 2026-11-12
SGLang Neuron is now publicly available through an AWS Deep Learning Container.
AWS Machine Learning Blog - aws.amazon.com · 2026-11-12
Oral exams are compelling because (1) students can be asked to provide their reasoning for an answer and (2) their interactive nature permits follow up questions to resolve ambiguous answers.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
I covered this topic live with Shishir Tewari, Senior Manager, Data Engineering at Procore, during GitHub Universe 2026. Our session was titled "Build once
The GitHub Blog - github.blog · 2026-11-12
Agents that perform state estimation using pretrained perception models, e.g., Vision-Language Models (VLMs)
arXiv coding-agent research feed - arxiv.org · 2026-11-13
Federated learning (FL) enables independent data owners to train models collaboratively without centralizing raw data.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
Rotating carousel of cards with text "Gemini 4 Hydrogen" "Now in Google Search" and examples from the Google Search UI
Google AI Blog - blog.google · 2026-11-12
Agentic AI systems increasingly undertake extended tasks and act on people's behalf
arXiv coding-agent research feed - arxiv.org · 2026-11-13
As autonomous AI agents increasingly interact in persistent populations, their collective capabilities and alignment depend not only on individual models, but also on the institutions governing their interactions.
arXiv Coding-Agent Research - arxiv.org · 2026-11-12
Upgrade Remotion, related packages, compatible Mediabunny packages, and installed Remotion Agent Skills
Remotion Documentation - www.remotion.dev · 2026-11-12
Agents in multi-agent systems that span organizational boundaries often need to collaborate in a composable, interoperable way, with agents that other organizations build and run
AWS Machine Learning Blog - aws.amazon.com · 2026-11-12
Get quick answers with Gemini in Chrome.
Google Blog All Topics - blog.google · 2026-11-12
The pypi registry records Google Gen AI SDK version 3.3.0.
PYPI Google Gen AI SDK - pypi.org · 2026-11-12
The pypi registry records LangGraph version 1.2.21.
PYPI LangGraph - pypi.org · 2026-11-12
The npm registry records Vercel AI SDK version 7.0.172.
NPM Vercel AI SDK - www.npmjs.com · 2026-11-13