Knowledge catalogue
arXiv:2605.23826v1 Announce Type: cross Abstract: Keyframe selection is a direct way to provide verifiable visual evidence for long-video question answering (QA). Queries differ in what they require,
The Pope rightly warns that AI must serve human dignity, not become a tool of domination or exclusion. But if we hand governments sweeping power over AI development in the name of safety, how do we pr
Nicole Nguyen / Wall Street Journal: Hands-on with a pre-release build of Google Docs Live, an AI-powered voice tool for drafting documents, rolling out this summer to AI Pro and Ultra subscribers — A
🦔This one happened yesterday but is still worth flagging. Starbucks killed its AI-powered inventory counting tool after nine months in North American stores. The system used LiDAR sensors and cameras
arXiv:2605.21605v1 Announce Type: new Abstract: Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal
arXiv:2511.20785v3 Announce Type: replace Abstract: Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hall
these guys built a research agent with activegraph (using their @monid_ai tool) and found that every claim was traced to a source - which is not prompted, but natively baked in to the approach (they a
code interpreter is a light weight code execution environment lets you do: - RLMs - programmatic tool calling - more! without having to spin up a full sandbox we'll be writing a lot more about the use
arXiv:2605.19151v1 Announce Type: new Abstract: We formalize trust calibration for agentic tool use (deciding when an automated agent's proposed action may execute autonomously versus require human ap
Fascinatingly Antigravity is actually the best tool so far at providing this sort of transparency, doing something by default that Codex and Code do not: offering a summary of exactly what it did at t
Jessica Conditt / Engadget: Google updates Project Genie, its interactive world builder, with Street View integration, and expands access to the tool to AI Ultra subscribers globally — Ground your sno
Deutsche Börse developed a generative AI tool to automate the migration of Zeppelin notebooks to Databricks at scale, addressing the complexity of converting legacy notebook formats. The solution leve
In this post, we show three ways to implement Programmatic tool calling (PTC) on Amazon Bedrock: a self-hosted Docker sandbox on ECS for maximum control, a managed solution using Amazon Bedrock AgentC
Zinnia Lee / Forbes: Shenzhen-listed RoboTechnik, which claims to be the largest silicon photonics tool maker and whose stock is up 340% over the past year, files for a HK listing — RoboTechnik Intell
Gary Marcus and Brian Greene discussed at the World Science Festival how scaling neural networks alone does not lead to artificial general intelligence, and that combining scaling with external tool u
Your agent also will now automatically have X Search tool available when using your Grok subscription as well! See details here: https://hermes-agent.nousresearch.com/docs/user-guide/features/x-search
EXCLUSIVE: Runway is one of the most interesting inflection point stories in AI right now. Started as a tool for filmmakers. Now going after world models/ universe simulation, and by extension, everyt
There is a case to be made that the future of Mathematics is very bright. In my mind, proofs have always been a tool to achieve a goal. The goal was and still is to understand, and reading/writing pro
arXiv:2602.16246v3 Announce Type: replace Abstract: Interactive large language model (LLM) agents operating via multi-turn dialogue and multi-step tool calling are increasingly used in production. Ben
Great example of why you should 1. Run your agent on a separate machine from the sandbox it uses (e.g. sandbox as a tool) 2. Never set env vars in your sandbox. Instead, use something like LangSmith’s
Emma Roth / The Verge: Netflix says its ad tier now has 250M monthly active viewers, up from 94M in 2025, and is expanding to 15 new countries, as it tests an ad personalization tool — The streaming s
One of the biggest challenges with agents is that they produce way more than just tokens. Tool calls. State updates. Intermediate reasoning. Subagent progress. File changes. Custom events. Structured
arXiv:2605.10787v1 Announce Type: new Abstract: Current LLM agents are proficient at calling isolated APIs but struggle with the 'last mile' of commercial software automation. In real-world scenarios,
arXiv:2605.09184v1 Announce Type: new Abstract: We present Open Ontologies, an open-source ontology engineering system implemented in Rust that integrates LLM-driven construction with formal OWL reaso
Simon Willison discovered how to use an LLM command-line interface tool in Unix shebang lines, enabling the creation of executable scripts written in English or natural language. This technique allows
real time model streaming audio/video/text in and out with tool use People talk, listen, watch, think, and collaborate at the same time, in real time. We've designed an AI that works with people the s
arXiv:2605.06483v2 Announce Type: replace Abstract: Signal Temporal Logic (STL) is an expressive formal language for specifying spatio-temporal requirements over real-valued, real-time signals. It has
100% agree on the Context Hub. Developers constantly tweak their approaches to manage context in their prompts with each new model and tool suite release. I would even say that the core problem we fac
@hwchase17 the tooling side is maturing fast but the feedback loop between engineers and domain experts is still the bottleneck. keep running into this building agents: you can instrument everything a
When your tool is open source and free, your creativity has no ceiling. The ComfyUI skill in @NousResearch Hermes Agent lets you compose sophisticated workflows by chatting to an agent. Try it today.
Finance Search is now available in the Perplexity Agent API. In one tool call, developers can now retrieve licensed financial datasets, real-time market data, and cited web sources for agents that nee
arXiv:2605.02728v1 Announce Type: new Abstract: This paper presents ORPilot, an open-source agentic AI system that translates real-world business problems into solver-ready optimization models. Unlike
Claude Code on desktop includes a preview feature that allows users to provide context to Claude by attaching DOM elements or drawing directly with a pencil tool. This functionality streamlines the pr
arXiv:2604.26511v1 Announce Type: cross Abstract: Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences o
The San Francisco–based startup Goodfire just released a new tool, called Silico, that lets researchers and engineers peer inside an AI model and adjust its parameters—the settings that determine a mo
We're launching early access to Gizmo, our automated sim creation tool. From text and/or image inputs, our agent generates SimReady assets and scenes from dimensioned primitives, with correct affordan
arXiv:2510.17548v2 Announce Type: replace Abstract: Language models are often evaluated with scalar metrics like accuracy, but such measures fail to capture how models internally represent ambiguity,
ComfyUI is the most flexible, composable, and powerful open-source media generation tool with a massive ecosystem of workflows and custom nodes. Your Hermes Agent can now install, launch, manage, and
First I'm going to install deepagents cli. This is a CLI which will help me set up and then deploy my agent `uv tool install deepagents-cli` DeepAgents CLI is open source - see it here: https://github
I released LLM 0.32a0 this morning, a major backwards-compatible refactor of my LLM Python library and CLI tool for working with language models - the new changes should help LLM work better with reas
We've open-sourced a few starter projects for you to build on: a coding agent CLI, a prototyping tool, and an agent-powered kanban board. Use Cursor to customize them for your use case: http://github.
arXiv:2604.14989v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have sparked growing interest in automatic RTL optimization for better performance, power, and area
introduced our new portfolio monitoring tool reads attio (crm), gmail, and granola notes, extracts data, and turns it into a timeline of quantitative and qualitative data points for each portfolio com
Nemotron 3 Nano Omni is now in LM Studio! A new 30B multi-modal MoE from @nvidia Supports Image input, reasoning, and tool use Requires ~25GB to run locally 🔥🚀 https://lmstudio.ai/models/nemotron-3-om
The most powerful real-time visual tool in creative coding also has the steepest learning curve Now your Hermes agent can just run TouchDesigner for you. Video credit: made by @macbethAI, a talented A
This is the tool: https://x.com/satyanadella/status/2048882283164389661?s=20 Agent Mode is here in Outlook! Copilot can now help run your inbox and calendar, triaging emails, rescheduling meetings, an
Which matters most? 1) Token usage 2) Dictation word count 3) Total AI queries 4) Tool count (Number 2 is becoming more and more of a positive indicator in my book, although I'm disappointed I broke m
A completely local agent that lives right inside your browser. Powered by Gemma 4 E2B and WebGPU, it uses native tool calling to: 🔍 Search browsing history 📄 Read and summarize pages 🔗 Manage tabs 100
@badlogicgames Yup: https://x.com/antirez/status/2048344770234249588 The GGUF tool calling template is wrong but I'm uploading a new GGUF file. Otherwise there is the right template file in one of the
If you believe that AI is going to have a big impact on work and life, the only real tool for mitigating bad impacts and channeling usage for good will be government policy And that policy will be com
After 2.1.117, you may notice that Claude doesn't call its Grep or Glob Tool anymore. YES!!! It only took four months. It's faster than ever and it's all Bash. It's so much harder to take things away
OpenAI: OpenAI releases ChatGPT for Clinicians, a tool for medical tasks like documentation and research, free for verified physicians, pharmacists, and more in the US — Built for clinical work, ChatG
Presumably GPT-imagegen-2 (aka ChatGPT Images 2.0 aka gpt-image-2) works as a tool which the models generate prompts for? I wish we could see those prompts, like back in the DALL-E 3 days https://simo
Qwen3.6 27B is now in LM Studio! Vision, reasoning, and agentic tool calling - running locally on your computer. Surpasses previous Qwen models many times its size 🚀👾🔥 https://lmstudio.ai/models/qwen/
arXiv:2511.14846v2 Announce Type: replace-cross Abstract: Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and ver
arXiv:2604.16706v1 Announce Type: cross Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated a
Tiffany Ng / Wired: How GrapheneOS lead developer Daniel Micay's legal fights with his former partner James Donaldson over CopperheadOS led to the privacy-focused tool's creation — There's a lot of lo
ICYMI: Kimi K2.6 is now in Notion. It’s the first open-weight model that plays like other top-tier models. It’s strong at tool use and carrying out tasks no matter how meticulous or ambiguous. Give it
arXiv:2512.07407v2 Announce Type: replace Abstract: Language models frequently produce plausible yet incorrect reasoning traces that are difficult to verify. We investigate fine-tuning models to use P
arXiv:2604.16538v1 Announce Type: cross Abstract: Automatic translation of natural language mathematics into faithful Lean 4 code is hindered by the fundamental dissonance between informal set-theoret