Knowledge catalogue
More than half of Cognition's first 50 employees were former founders. @ScottWu46 sat down with @breeves08 and @lux_capital to talk about correctness over comfort, staying focused on our mission, and
A discussion on building an AI-powered article generator using CrewAI and Ollama with specialized AI agents for research and writing to generate comprehensive articles on any topic. The solution runs
NitroGen just won CVPR Best Paper Honorable Mention!! We are making strides towards general-purpose embodied agents that master not only the real world physics, but also all possible physics across a
arXiv:2602.05843v2 Announce Type: replace Abstract: The rapid advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments.
arXiv:2605.25970v2 Announce Type: replace Abstract: Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical tria
arXiv:2606.05275v1 Announce Type: new Abstract: We study the personal camera roll visual question answering setting. In this setting, a conversational AI assistant can access a user's personal camera
arXiv:2606.06014v1 Announce Type: cross Abstract: Latent world models (LWMs) have strengthened end-to-end autonomous driving by forecasting compact scene dynamics for downstream planning. However, exi
arXiv:2606.05896v1 Announce Type: new Abstract: Creating lifelike digital humans with genuine social intelligence requires unifying cognitive reasoning and multimodal generation within a coherent fram
arXiv:2606.05922v1 Announce Type: cross Abstract: AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to
arXiv:2506.10145v3 Announce Type: replace Abstract: End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into th
Sandboxes are already helping teams move from agents that answer questions to agents that can do work safely. At @mondaydotcom, that means giving Sidekick a secure environment to write and run code fo
This post likely covers a live broadcast or announcement discussing the integration of Shopify with Replit, along with information about a newly released SEO Agent tool. The content probably demonstra
arXiv:2606.06079v1 Announce Type: new Abstract: Agent skills, which consist of reusable strategies that guide agent reasoning and action, have shown strong potential for improving model capability at
arXiv:2606.05890v1 Announce Type: new Abstract: LLMs are increasingly deployed as Artificial Moral Advisors (AMA) in a variety of contexts: what kind of conversational patterns should they display? In
Tesla's Cybercab is positioned as a revolutionary autonomous vehicle that Elon Musk claims will fundamentally transform transportation and road infrastructure through fully self-driving technology. Th
Cognition AI shared a video hosted by Lux Capital, with a link to the full video on YouTube. The post appears to be a thank you message acknowledging Lux Capital's role in hosting an event or discussi
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. The Meta hack shows there’s more to AI security than Mythos On
// The Meta-Agent Challenge // How good are current agents at self-improving? This is a great paper covering some of the challenges. They propose the Meta-Agent Challenge (MAC), where they give a codi
On June 5, 404 Media reported that attackers had been using Meta’s AI customer support agent to steal Instagram accounts. Their approach was simple: They asked the agent to link the accounts to email
arXiv:2606.05976v1 Announce Type: cross Abstract: Recent work shows that LLM agents struggle to correct errors in their own reasoning traces yet show markedly higher correction rates when identical cl
Thousand Token Wood is a multi-agent economy simulation built on a 3 billion parameter language model, demonstrating how small models can power complex interactive systems with multiple agents. The pr
arXiv:2606.06416v1 Announce Type: cross Abstract: Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updati
arXiv:2606.05848v1 Announce Type: new Abstract: In this paper, we present a robotic ultrasound acquisition system that integrates stereo vision, touch-based feedback, and expert-informed strategies to
LangSmith Engine, a tool by LangChain, helped Odessa Travel improve their development workflow by converting execution traces into actionable bug fixes, making debugging more accessible to their team,
1/ 🔥 @NoPriorsPod x @LatentSpacePod chat with @SatyaNadella at @Microsoft Build. He has the sharpest mental models of any public company CEO I've interviewed. $MSFT is at its heart still a tools compa
AI21 Labs discusses how the order of operations in agent pipelines affects performance, presenting findings that reversing the typical 'scale first, enrich second' approach by instead enriching agent
Databricks presents Instructed-Retriever-1, a system that achieves 3x faster search performance through parallel test-time scaling techniques. The approach optimizes retrieval operations by executing
The rise of agentic commerce is forcing retailers to rethink their entire data strategy — not as a future concern, but as the immediate prerequisite for competing in a world where AI agents make purch
AI should earn its keep. Introducing the AI Productivity Guarantee. If Devin delivers less engineering value than you’re paying for, Cognition will fund your usage until it does, up to $10 million. It
Amazon has announced a new version of its fully autonomous warehouse robot, Proteus, that will interact using language instead of code. The expanded capabilities come as part of a growing pivot toward
arXiv:2606.04755v1 Announce Type: cross Abstract: We present Archi, an open-source, end-to-end framework for scientific collaborations that combines the systematic ingestion and organization of hetero
Witan Labs is developing a headless Office stack designed specifically for AI agents, combining productivity tools and capabilities without a traditional user interface. This post appears to be a week
arXiv:2510.13272v3 Announce Type: replace Abstract: Inspired by the success of reinforcement learning (RL) in Large Language Model (LLM) training for domains like math and code, recent work has begun
arXiv:2606.04494v1 Announce Type: new Abstract: Biomedical agents promise to automate complex biological workflows, yet current systems face two fundamental bottlenecks: bioinformatics tools are highl
arXiv:2510.17064v4 Announce Type: replace Abstract: Single-cell RNA sequencing has transformed our ability to identify diverse cell types and their transcriptomic signatures. However, annotating these
Jerry Liu announced plans to significantly increase marketing budget allocation by 10x, likely discussing strategy for scaling marketing efforts or business growth initiatives. The post appears to be
Arize AX is adding managed agents, full-agent experimentation, expanded multimodal support, and Harness-as-a-Judge to help teams observe, evaluate, and improve production agents. The post Building the
arXiv:2606.04746v1 Announce Type: new Abstract: Multi-Agent Path Finding (MAPF) algorithms are increasingly used to plan motion for robot teams in industrial warehouses and robotic shared workspaces,
This post likely announces or describes how to invoke or utilize a Hermes Agent, possibly related to function calling, tool use, or agentic capabilities within the Hermes model framework developed by
arXiv:2606.04435v1 Announce Type: new Abstract: Multi-step agentic retrieval-augmented generation (RAG) pipelines have demonstrated significant capability for complex reasoning tasks, yet remain vulne
Mark Tyson / Tom's Hardware: Cloudflare CEO Matthew Prince says agentic traffic is “growing so fast that bots have now passed human traffic online for the first time” — Bot (automated) vs. human HTTP
arXiv:2606.04223v1 Announce Type: new Abstract: Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation. We argue th
arXiv:2603.10971v2 Announce Type: replace-cross Abstract: Reinforcement learning has achieved remarkable success in domains such as Atari games, navigation, and locomotion, where exploration can often
Cursor can now show your agent's context usage as an interactive report in a canvas. The context explorer breaks down where tokens go across the system prompt, tool definitions, rules, skills, and mor
arXiv:2606.05009v1 Announce Type: cross Abstract: Deontic reasoning is the task of answering questions by applying explicit rules and policies to case-specific facts, for example computing tax liabili
arXiv:2606.04360v1 Announce Type: new Abstract: Symbolic regression (SR) discovers compact mathematical expressions from data, yet recent LLM-based evolutionary methods remain sample-inefficient becau
arXiv:2606.04769v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has emerged as a critical standard empowering Large Language Models (LLMs) to utilize external tools. In this ecosyst
The Hugging Face CLI (command-line interface) is designed as an agent-optimized tool that enables AI agents and users to interact with the Hugging Face Hub more efficiently. The design prioritizes com
arXiv:2602.14885v2 Announce Type: replace-cross Abstract: Recurrent neural networks (RNNs) provide a theoretical framework for understanding computation in biological neural circuits, yet classical re
arXiv:2606.04492v1 Announce Type: new Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) frequently suffers from severe reward sparsity and exploration bottlenecks. While episodic memory
arXiv:2606.04315v1 Announce Type: new Abstract: LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems. Yet most existing designs are tun
arXiv:2606.04751v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents in scientific tasks. Yet whether these systems can effectively engage in for
Fireworks was named to @Redpoint's InfraRed 100 which recognizes the companies building the foundation for the next wave of AI. We're just getting started. Come build with us: https://fireworks.ai/car
From idea to live store, in minutes. 🛍️ Tomorrow on the Friday Showcase: → Replit's new Shopify partnership, with @Davidizek . Tell Replit Agent what you want to sell and it builds your storefront, cr
arXiv:2606.04967v1 Announce Type: cross Abstract: AI tools for programming are no longer just autocomplete or chat assistants: they organize themselves as development frameworks, with process, roles,
arXiv:2507.21892v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that l
Harrison Chase, co-founder of LangChain, shares insights on the future development and evolution of AI agents in this Twitter thread. The post likely covers emerging trends, technical capabilities, an
here’s why i think the situation may be dire: https://x.com/GaryMarcus/status/2062369417372258652?s=20 ⚠️Why didn’t the hyperscalers wait until after the IPO in switching to pay-by-usage-charging? My
arXiv:2606.04437v1 Announce Type: new Abstract: Collaborative perception extends the perceptual range of autonomous vehicles by sharing information across agents, but heterogeneous sensors and percept
its been such fun befriending Pari and seeing him completely reinvent his company for the agentic era, WHILE having the most insanely stacked customer base I've ever seen in the hardest engineering do