Knowledge catalogue
Replit announced support for image generation capabilities using GPT-Image 2, video creation with Seedance, and the ability to create animated SVGs, expanding the platform's generative AI features. Th
arXiv:2606.01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) an
arXiv:2606.02470v1 Announce Type: new Abstract: The Model Context Protocol (MCP) has emerged as a transformative standard for connecting large language models (LLMs) with external data sources and too
arXiv:2606.00152v1 Announce Type: cross Abstract: LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. However, agents often acquire mor
arXiv:2606.00593v1 Announce Type: cross Abstract: Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has imp
arXiv:2605.31042v1 Announce Type: cross Abstract: LLM agents are evolving from conversational chatbots to operational tools in real-world workspaces. In local agentic harnesses, an LLM can read and wr
The example of a growing restaurant Imagine you are running a restaurant chain. You just can't physically feel and touch things to know how your business operates. You need tools and a digital replica
This post links to a Latent Space article providing a comprehensive writeup and resources about video agents, likely covering AI systems that can understand, analyze, and generate video content. The a
Vercel's Chat SDK has expanded its integration capabilities to support Lark and Feishu, two popular communication and collaboration platforms. This addition enables developers to build chat applicatio
arXiv:2605.29129v1 Announce Type: new Abstract: Agentic AI systems are increasingly being explored as production infrastructure: they reason over multiple steps, call tools, act through workflows, and
Amazon OpenSearch Serverless integration is now available through the Vercel Marketplace, enabling Vercel users to easily connect serverless search and analytics capabilities to their applications. Th
As AI agents handle increasingly complex tasks with extended context windows, the cost structure of LLM usage has shifted such that input tokens now represent the majority of price-equivalent expenses
arXiv:2605.27922v1 Announce Type: new Abstract: LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, perform
arXiv:2605.27489v1 Announce Type: cross Abstract: Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretabilit
This Latent Space article discusses emerging AI infrastructure companies valued at $1 billion or more (decacorns), with a focus on Fireworks AI and the broader landscape of companies building foundati
Reachy Mini, a robotic system, can now operate with fully local processing capabilities, enabling on-device inference without requiring cloud connectivity. This advancement allows the robot to run AI
arXiv:2605.26275v1 Announce Type: new Abstract: Automatic prompt engineering (APE) rewrites prompts to improve downstream task performance, but existing APE loops treat the optimizer itself as a fixed
arXiv:2605.26128v1 Announce Type: new Abstract: Production LLM systems increasingly require machine-readable outputs: JSON objects, typed traces, regex-constrained fields, and tool-call schemas. This
arXiv:2510.17790v3 Announce Type: replace-cross Abstract: Computer-use agents face a fundamental limitation. They rely exclusively on primitive GUI actions (click, type, scroll), creating brittle exec
arXiv:2605.21850v1 Announce Type: new Abstract: Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly lo
arXiv:2605.20210v1 Announce Type: cross Abstract: Agentic AI systems - systems that can pursue goals through multi-step planning and tool-mediated action with limited direct supervision - are moving f
This post from Swyx likely discusses emerging AI infrastructure companies that have recently achieved unicorn status (valued at $1B+), covering new players disrupting the AI stack beyond major cloud p
arXiv:2605.22104v1 Announce Type: new Abstract: Real-world image restoration is challenging due to complex and interacting mixed degradations. Recent agent-based approaches address this problem by com
arXiv:2605.21413v2 Announce Type: new Abstract: As AI becomes part of everyday learning, many courses teach students to use it mainly as a productivity tool: how to prompt, search, summarize, write, c
arXiv:2605.20530v1 Announce Type: cross Abstract: Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but the benchmarks used to evalu
The Vercel Chat SDK has been updated to include message subjects functionality and direct SDK access capabilities. This enhancement allows developers to organize and manage chat messages more effectiv
Microsoft Senior AI developer just showed how they build AI agents with Claude at Microsoft. 34-minutes. free. By Microsoft team Opus 4.7 + 1,400+ pre-built MCP tools plug Claude into agent → give it
arXiv:2605.18805v1 Announce Type: cross Abstract: LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet ex
arXiv:2605.17281v1 Announce Type: cross Abstract: Tool-augmented LLM agents call APIs whose intermediate outputs, such as presigned URLs, session tokens, and OAuth state parameters, are observation co
datasette-llm-accountant is a plugin that handles allowances and estimated pricing features for Datasette LLM usage. It works with datasette-llm and datasette-llm-limits to let users configure spendin
arXiv:2602.16346v3 Announce Type: replace Abstract: LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to ca
arXiv:2605.16286v1 Announce Type: cross Abstract: Different AI tools such as ChatGPT, Gemini, and Claude are becoming very popular. Although they are helpful for many day-to-day tasks, they can be use
arXiv:2605.17758v1 Announce Type: new Abstract: Synthetic data is widely used in healthcare to create datasets that are similar to original data but without the privacy concerns. Generating and evalua
arXiv:2605.16623v1 Announce Type: cross Abstract: Large language models are increasingly discussed and used as tools that may assist with scholarly peer review, but empirical evidence regarding how au
Today, we’re announcing Viktor’s 75M Series A, led by @Accel . @viktor__com was supposed to be a small experiment. It became the AI coworker 10x'ing real businesses. 15M in annualized revenue run rate
A mother who builds is a mother worth celebrating. Sara is an Associate Professor of Nursing at Miami University, and a mother of two adult kids, one baby, a beagle, and a cat. She teaches pharmacolog
Vercel announced the availability of consolidated commit status functionality for GitHub, which likely streamlines how deployment and build statuses are displayed and managed within GitHub's interface
This is exactly what we're seeing. The 'AI for everything' era is really the 'software for everyone' era. Every SMB becomes a software company. You don’t need to build the next J.A.R.V.I.S. You need t
arXiv:2605.14084v1 Announce Type: cross Abstract: Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these cap
This appears to be a humorous exchange from X/Twitter creator Harrison Chase referencing train cars named after AI/ML tools and services (Devin, Langsmith, and Mistral), likely making a joke about the
arXiv:2605.14237v1 Announce Type: new Abstract: Deploying AI agents for repetitive periodic tasks exposes a critical tension: Large Language Models (LLMs) offer unmatched flexibility in tool orchestra
Doing this is a great way to make a bonfire of your reputation A person I know (and who is? was? a good professional al) left an AI-generated comment under my LinkedIn post. Full-on AI slop. I asked:
AutoScientist is an AI system developed by Together AI that automates the complete research workflow to enable model training and scientific discovery outside of well-resourced frontier laboratories.
This was a live broadcast from SaaStr (a SaaS industry conference), streamed on X by Replit on Day 2 of the event. The 'Midday on the Floor' segment likely featured live updates, interviews, or discus
arXiv:2605.11167v1 Announce Type: new Abstract: Existing multi-model and tool-augmented systems communicate by generating text, serializing every exchange through the output vocabulary. Can two pretra
arXiv:2510.13896v2 Announce Type: replace-cross Abstract: Cellular image segmentation is essential for quantitative biology yet remains difficult due to heterogeneous modalities, morphological variabi
Highlights: 👉 600+ voices across MiniMax, Cartesia, Deepgram, Rime, and more 👉 Search by prompt or audio sample 👉 Filter by 15+ attributes, including pitch, accent, language, age, emotion, and speakin
arXiv:2605.09131v1 Announce Type: new Abstract: The Model Context Protocol (MCP) has unified the interface between Large Language Models (LLMs) and external tools, yet a fundamental gap remains in how
arXiv:2605.08876v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical f
Vibecon is a conference hosted by Replit taking place in New York City on June 17-18 that features speakers and discussions about code-as-medium and the future of creative coding. The event brings tog
arXiv:2603.23806v2 Announce Type: replace-cross Abstract: AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invoca
Dealing with quirks introduced by switching models doesn't have to be hard -- we recently introduced a 'harness profile' API in Deep Agents as a solution. Profiles adjust system prompts, tool descript
Simon Willison shares a technique for using Large Language Models directly from the command line using a shebang (#!) syntax, allowing scripts to be executed with LLM processing without explicit comma
arXiv:2605.06812v1 Announce Type: new Abstract: LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and mult
This article was updated after The Times learned that a remark attributed to Pierre Poilievre, the Conservative leader, was in fact an A.I.-generated summary of his views about Canadian politics that
Vercel's Chat SDK now includes web adapter support, enabling developers to integrate chat functionality into web applications more seamlessly. This enhancement expands the SDK's compatibility and make
Today, we’re thrilled to announce that Gemini 3.1 Flash-Lite, our fastest and most cost-efficient Gemini 3 series model yet, is now generally available. Designed for ultra-low latency, high-volume tas
Swyx posted an enthusiastic endorsement of using Devin AI as a social media advisor, directed at Jacob Effron, highlighting what appears to be impressive capabilities or results demonstrated by the to
arXiv:2605.02913v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these syst
Building AI agents that work well in a demo is one thing, but running them in production requires serious infrastructure. At Google Cloud Next '26, we introduced Gemini Enterprise Agent Platform to he