Knowledge catalogue
arXiv:2609.36576v1 Announce Type: new Abstract: Agentic systems are now being widely used to orchestrate tools and reason over long contexts. However, the improving capabilities of the large language
arXiv:2609.35381v2 Announce Type: replace-cross Abstract: Many Model Context Protocol (MCP) servers wrap web APIs built for human developers, and their error messages tell the reader to run a command,
arXiv:2609.37968v1 Announce Type: new Abstract: Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures. Existing app
arXiv:2609.37172v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as powerful tools for automated heuristic design (AHD), enabling iterative generation and refinement of heuris
arXiv:2609.33772v2 Announce Type: replace Abstract: Executable environments are critical for post-training agents on tasks that require tool use and multi-step interaction, but constructing executable
arXiv:2609.37953v1 Announce Type: new Abstract: Complex tasks inherently couple workflow structure, agent responsibility, collaboration, and memory access: task regions delimit responsibility and tool
Perplexity AI released a preview of its embedding model “pplx‑embed‑v2‑context‑9b” on Hugging Face on September 30, 2026 (7:07 PM local time). The Hugging Face repository page displays 3 122 views and
arXiv:2609.38086v1 Announce Type: new Abstract: Active multimodal agents use visual tools to acquire task-relevant evidence while reasoning. Although reinforcement learning samples multiple interactio
Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact
We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view. pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB a
arXiv:2609.33371v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents turn credential hygiene from a storage problem into an execution-security problem. A key pasted into a pr
arXiv:2609.33260v1 Announce Type: cross Abstract: An agent can solve a task today and face the same task under new facts, tools, or governing knowledge tomorrow. Most agent systems can retrieve releva
arXiv:2609.33060v1 Announce Type: new Abstract: Speech therapists often face difficulties diagnosing impairments due to the lack of efficient tools for transcribing speech into the International Phone
arXiv:2609.31632v1 Announce Type: new Abstract: Electroencephalography (EEG) analysis is evolving from short-segment classification toward long-horizon interpretation that demands iterative evidence a
Good Just arrived at @OpenAI #DevDay, and I’m predicting proactive intelligence will steal the show. We’ve gone from statistics to machine learning to intelligence. Now the next step is AI that doesn’
My comment on GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price — Hacker News.I'm a bit late with the pelicans because I was live-blogging the keynote: https://simonwillison.net/2026/Sep/2
arXiv:2609.35427v1 Announce Type: new Abstract: Modern LLMs are increasingly capable as autonomous agents, but they follow sequential interaction cycles: read, think, reply or call tools, repeat. Many
arXiv:2609.34572v1 Announce Type: cross Abstract: Reasoning language models that can call tools must decide during inference whether to answer unaided or delegate. Any self-reflection mechanism for th
I'm at OpenAI DevDay today, in Fort Mason, San Francisco. Same as last year I'll be live blogging the keynote and some other notes during the day. OpenAI gave me a free ticket and a seat in the 'creat
arXiv:2609.35432v1 Announce Type: new Abstract: Vision-language-action (VLA) and world-action (WAM) models map observations and instructions directly to robot actions. This directness ties a policy to
So dots are either your amplifier or your additional team member, although right now you can have one dot - why? Because otherwise things will get really messy in this new human-AI multiplayer game. T
Together is #1 on @OpenRouter token share across top open coding models, today: 🥇 @Zai_org GLM 5.3 Flash: 29.2% 🥇 @deepseek_ai V4.1 Flash: 25.6% 🥇 @Kimi_Moonshot Kimi K3: 18.9% Running coding agents o
arXiv:2609.31358v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) provides a common interface through which AI applications discover and use external resources and tools. It allows la
arXiv:2609.31569v1 Announce Type: cross Abstract: Conversational AI tools are entering children's everyday experiences, and schools are interested in adopting them. However, successful classroom integ
arXiv:2609.31318v1 Announce Type: cross Abstract: AI agents combine language models with external data and tools that can modify files, call APIs, or execute code. Security failures can arise when adv
arXiv:2609.31430v1 Announce Type: new Abstract: Tool observations dominate the context of software-engineering agents, making long interaction histories costly to maintain. Existing context compressio
every agent will need a sandbox and the harness should live outside it - separate the brains from the hands great to see nvidia open sourcing tools here, agree with Andrew this is part of the harness
Excited to share that I'll be speaking at @aiDotEngineer NYC on Oct 12-14. @covacut (@OpenAI) and I will be giving a joint talk about using AI for content creation, and some of the AI workflows behind
Apple Silicon Macs on macOS 26+ come with a small LLM built in. No download, no API key, and nothing leaves your Mac. Why I built it I was making a tool that writes API docs from code, and I didn't wa
arXiv:2609.30836v1 Announce Type: new Abstract: Deploying small language models (SLMs) on offline, resource-constrained edge devices such as remote sensing satellites presents a fundamental challenge:
I tested Jev and five LLM judges across ten Arize Phoenix evaluators to measure how often their answers changed alongside accuracy, cost, and latency. The post What Jev’s probabilities reveal that rep
arXiv:2609.29647v1 Announce Type: cross Abstract: Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instructions, persist intermediate belief
arXiv:2609.29744v1 Announce Type: cross Abstract: We present: (i) a new dataset consisting of the full development history of a 21,000-line Python tool built entirely by Claude AI, with no human-autho
arXiv:2609.30050v1 Announce Type: new Abstract: We present NNV3, the latest version of the Neural Network Verification (NNV) tool, a MATLAB framework for formal verification of deep learning models an
Reliable, fast inference is essential. As Ted shared at Apsara Conference 2026, Together makes it easy for teams to get access to frontier open models without needing to manage any of the infrastructu
I have a tool that uses Gemini Flash with the lowest thinking budget to do summarization work. It's very fast, 0.9-1.2s in most cases. But I have a user experience problem where people make the wrong
Want to RL-train a model on your own task without building the infra? Use our new cookbook with @hud_evals: → Define your task + grader in HUD → Sample + train the model on Fireworks Define the task o
arXiv:2609.28559v1 Announce Type: cross Abstract: LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files. Substituting the model behind such
Amazon.com Inc. said today it’s trying to make life easier for independent sellers using its ecommerce platform with new tools including a plugin that allows them to run their businesses via artificia
The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder. We can do amazing things with them, but unlocking their full potential requir
Following our announcement of Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking last week, we are thrilled to share that Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enter
arXiv:2609.27855v1 Announce Type: new Abstract: AI systems increasingly claim to optimize prompts, policies, architectures, plans, tool-use trajectories, reasoning traces, and test-time computation. T
Scribd, Inc. is home to one of the world's largest collections of human-created content. Scribd’s products leverage one of the world's largest collections of human-created content and intelligent tool
arXiv:2609.28372v1 Announce Type: cross Abstract: Consumers increasingly delegate purchasing decisions to Large Language Models (LLMs) acting as surrogate consumers. Using 'Tool-Lab,' an adaptation of
Today, @FactoryAI joins the Specialized Intelligence Index with Legacy-Bench! The SII keeps growing, now with benchmarks testing how models handle the legacy software behind payroll, financial settlem
Title: **'When Chat Is the Wrong UI'** Burke Holland (@burkeholland) is a technologist, author, speaker, and creator who works at GitHub, where he focuses on AI‑powered development. In his talk or art
arXiv:2609.22476v1 Announce Type: cross Abstract: Transmission system operators face rising complexity from renewable integration, reduced inertia, and tighter security margins. Large language models
arXiv:2609.24165v1 Announce Type: new Abstract: Synchrotron data reduction, detector calibration followed by azimuthal integration of terabyte-scale diffraction series, is a multi-step, expert-bound b
ARCv3 is Fireworks' new compressor for RL. It cuts the size of BF16 weight updates by nearly 50%, which makes cross-region training more practical and keeps rollouts current. For teams using their own
Radical Numerics, led by CEO Eric Nguyen, is deploying “biological chain‑of‑thought” and multimodal perception techniques to stay ahead of the evolving bio‑defense arms race, enabling rapid design of
arXiv:2609.23894v1 Announce Type: cross Abstract: Agentic AI extends LLM security beyond generated content to persistent state, autonomous actions, tool use, and interactions with humans and other age
Tool: Gemini 3.8 TTS Playground Google released two new Gemini text-to-speech models today - gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts. They come with a library of over 2,000 voices, plus the
How we rebuilt the diff surface in the GitHub Copilot app to open a million-line pull request with hundreds of inline review comments. The post Rendering huge pull requests in the GitHub Copilot app a
Training can cut costs by up to 90% on the work your customers depend on. The next model drop won’t get you there, no matter how great it is. Join us and @Macroscope's @Rob_Bishop as we chat about own
arXiv:2609.24362v1 Announce Type: new Abstract: Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language mo
arXiv:2609.22194v1 Announce Type: new Abstract: Enterprise analytics agents solve long-horizon tool-use problems over distributed business data, requiring retrieval, reasoning, API calls, code executi
arXiv:2609.22114v1 Announce Type: new Abstract: Context compression is widely proposed as a way to cut the token bill of LLM coding agents, and public benchmarks report that aggressive compression pre
arXiv:2609.23490v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly execute multi-step workflows through tool use and interaction with users and environments. However, curre
arXiv:2609.22949v1 Announce Type: cross Abstract: Existing prompt injection research focuses on single-model chatbot scenarios, where an attacker manipulates one LLM through crafted input. Multi-agent
GPT-6 Luna is half the price of 5.6 Luna, which was already an astonishingly cheap model given how capable it is Luna is my favorite model for building product features thanks to its cost (and speed)