Search: “agents”

Deep Agents supports sandboxes from any provider; with first-class support for E2B, Daytona, LangSmith, Modal, Vercel, Runloop, AgentCore, and BYOS (bring-your-own-sandbox implementation) support http

arXiv:2606.27499v1 Announce Type: cross Abstract: Research on agent memory has matured rapidly, but almost entirely on the text side: few existing benchmarks ask, in an interactive environment, when a

arXiv:2606.27483v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-hor

arXiv:2606.27397v1 Announce Type: cross Abstract: Evaluating LLM agents requires dynamic environments that go beyond static reasoning and zero-sum games. Real-world economic interaction is often open-

Cursor's Live Activities feature enables real-time notifications to keep users informed when AI agents complete tasks or require user input during development workflows. The feature supports reviewing

arXiv:2606.28061v1 Announce Type: cross Abstract: Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments

We are starting to role out our Trace Judge model to early partners today Designed to detect errors in agent trajectories at 1/100th of the cost compared to closed models If interested in early access

We have more releases to come for Zenith & our sota open source II Agent, pushing the boundaries of novel & first principles reasoning Larger models will show strong numbers, but we've reached a point

arXiv:2606.27443v1 Announce Type: new Abstract: Personality prompting shapes how large language models communicate, yet whether these behavioral shifts affect objective task outcomes remains under-exp

Fleet agents can be shared in channels where your company is already doing work. Slack, Teams, etc Video from Caspar showing how to bring them into Slack! For agents to spread through a company they h

There's a big difference between a single model call and serving an agent at scale. @ZainHasan6 breaks down what actually changes. Catch our team this Monday at 9 a.m. PST for their open-source infere

arXiv:2603.09448v2 Announce Type: replace-cross Abstract: Delineating the clinical target volume (CTV) in radiotherapy involves complex margins constrained by tumor location and anatomical barriers. W

arXiv:2606.27330v1 Announce Type: cross Abstract: Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks in

Hermes Agent + Computer Use by @trycua is pretty cool! Looking at Hermes interacting with apps and windows is mind blowing and a bit scary at the same time 😂 Here on Mac with MiniMax M3 and Reachy Min

arXiv:2606.26575v1 Announce Type: cross Abstract: Complex multi-agent control tasks remain challenging for traditional rule-based and model-based approaches, motivating the adoption of learning-based

In a real conversation, deciding when to speak takes about as much brainpower as deciding what to say. Voice agents haven't been built that way. @SierraPlatform's unlock was parallelizing thinking, li

not trying to glaze but the hermes agent experience is so much better now it is running so much of our triage stuff now at ***** ai labs now, still have to correct/customize stuff every now and then b

One of my best uses of agentic loops has been personal health. I don't talk about it often because it's very personal. But here it goes in the hope it helps someone who's struggling. (I am not doing t

arXiv:2606.26123v1 Announce Type: cross Abstract: Ultra-low latency and high throughput are required for Virtual Reality (VR) services in 6G networks, which presents critical challenges for Software-D

arXiv:2606.26907v1 Announce Type: new Abstract: While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or d

The AI SDK Harness API now supports @OpenCode and @LangChain Deep Agents through a single unified interface. Use 𝙷𝚊𝚛𝚗𝚎𝚜𝚜𝙰𝚐𝚎𝚗𝚝 to run any supported runtime without changing your app code. https://verce

browser extension for hermes agent @NousResearch hermes lives on every tab🪽 - side panel chat on any page - swap models: opus, gpt, grok, local - session picker, vision + screenshots - connects to you

In this post, we show you how to build Chaplin (Customer Health and Planned Lifecycle Intelligence Nexus), an open source solution that uses AI agents exposed through the Model Context Protocol (MCP)

Vercel has released Deep Agents and OpenCode adapters for the AI SDK Harness, expanding the framework's integration capabilities. These new adapters enable developers to leverage Deep Agents and OpenC

This post likely describes how to integrate voice communication capabilities with Hermes agents, enabling two-way spoken interaction rather than text-only exchanges. It probably covers implementation

Replit now supports 450+ integrations. No matter what you're building, Replit Agent can wire it up to the tools you already use: payments, messaging, data, CRMs, design tools, analytics, and hundreds

arXiv:2606.18837v2 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. Howe

arXiv:2606.25335v1 Announce Type: new Abstract: Multi-Agent Reinforcement Learning (MARL) value factorization methods can suffer from a loss of plasticity, gradually failing to adapt when transferring

Vercel explores how to teach AI agents to understand and participate in product design processes, likely discussing methods for training agents to assist with design decisions, user experience conside

Technical blog on how we built SmithDB (our database purpose built for agent traces) How do you construct, compact, and query a full-text search index when all your durable data lives in object storag

arXiv:2606.26057v1 Announce Type: cross Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places co

arXiv:2606.25760v1 Announce Type: cross Abstract: Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejec

AI21 Labs announced achieving the #1 ranking on DeepResearch Bench II without developing any new agents, suggesting they improved performance through optimization of existing systems or methodology ra

arXiv:2606.24392v1 Announce Type: new Abstract: Existing ECG report generation is tightly coupled -- interpretation and reporting fused end-to-end, so errors propagate without stage-level recourse --

arXiv:2606.24453v1 Announce Type: new Abstract: Modern coding agents pair LLM generators with various tools, including cheap diagnostics and expensive verifiers. The tool-use decisions are typically g

arXiv:2605.06177v2 Announce Type: replace Abstract: Reproducing and comparing deep research agents today is hard: the same backbone evaluated on the same benchmark can report different accuracies acro

arXiv:2606.24151v1 Announce Type: cross Abstract: Self-evolving agents improve over time by distilling experience from past executions and reusing it in future tasks. Existing systems represent such e

Obsessed with our new /learn skill. It's my favorite way of learning and researching topics. The agent creates a learning plan and a learning hub (artifact) that adjusts per learner needs and progress

Kif Leswing / CNBC: Qualcomm unveils Dragonfly C1000, a new data center CPU built for agentic AI, and says Meta will use the chip when production starts in 2028 — Qualcomm shares jumped 15% in extende

arXiv:2606.24597v1 Announce Type: new Abstract: A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning.

arXiv:2606.24820v1 Announce Type: new Abstract: LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing. Dedicated l

Sometimes you just need a dose of fresh inspiration but your agent doesn't get the vibe. The creative-ideation skill analyzes your prompt and routes it through one of 22 creative methodologies from ar

arXiv:2606.24470v1 Announce Type: new Abstract: A real-time agent for general computer use - with games as the most demanding case - must act within tens of milliseconds while still planning over seco

arXiv:2606.24842v1 Announce Type: new Abstract: In the big-world regime, agents cannot be universally capable and their ability is inevitably specialized across a world model in pieces. Consequently,

You can now delegate tasks to Cursor directly from Notion. It's built on the Cursor SDK, so every cloud agent runs on the same models, harness, and runtime that power Cursor. @​Cursor on any spec or a

arXiv:2606.21013v1 Announce Type: cross Abstract: Forecasting future events is a critical challenge for large language model (LLM) agents, spanning domains from elections and monetary policy to financ