Search: “agents”

arXiv:2604.23366v1 Announce Type: new Abstract: Autonomous multi-agent LLM systems are increasingly deployed to investigate operational incidents and produce structured diagnostic reports. Their trust

I have been playing with the new Outlook agent, and it is fine, but really awkward to use, since you have to ask for things in a chatbot window, then go to your drafts, etc. And Claude Cowork does the

NVIDIA's Nemotron 3 Nano Omni is a lightweight multimodal AI model capable of processing documents, audio, and video inputs for building intelligent agents. The model supports long-context understandi

arXiv:2601.21321v2 Announce Type: replace Abstract: This paper proposes White-Op, an operational amplifier (op-amp) behavioral-level parameter design framework assisted by the human-mimicking reasonin

arXiv:2604.23970v1 Announce Type: new Abstract: Indoor navigation remains a critical accessibility challenge for the blind and low-vision (BLV) individuals, as existing solutions rely on costly per-bu

NVIDIA Nemotron 3 Nano Omni is a 30B hybrid mixture-of-experts model that brings multimodal perception and reasoning into a single system, natively supporting text, image, video, and audio inputs whil

OpenAI announced the availability of its models, including Codex, and managed agent capabilities on Amazon Web Services (AWS) infrastructure. This integration enables AWS customers to access OpenAI's

arXiv:2604.22934v1 Announce Type: new Abstract: LLM-based agents for text-to-SQL often struggle with latency-performance trade-off, where performance improvements come at the cost of latency or vice v

Ben Thompson / Stratechery: Q&A with Sam Altman and AWS CEO Matt Garman about OpenAI's new partnership with AWS, Bedrock Managed Agents, Trainium chips, and more — As I noted yesterday, today's Strate

Today we’re releasing Laguna XS.2, Poolside’s first open-weight model. It’s a 33B total / 3B active MoE model built for agentic coding and long-horizon tasks. Trained fully in-house on our own stack.

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

arXiv:2604.21937v1 Announce Type: new Abstract: Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specializ

ParseBench: A benchmark for document parsing agents @llama_index just shipped a benchmark with 2k verified pages for real enterprise documents. Benchmarks are the major underrated component in the ML

This post compares TensorRT-LLM and llama.cpp (GGUF) as inference frameworks for running coding agents like Cline and RooCode on RTX 5090 GPUs, examining the tradeoff between inference speed and VRAM

This is totally wrong. Blaming the user is missing the point that (a) coding agents have been overhyped and (b) can’t reliably obey the rules given to them in system prompts and other guardrails. Sorr

TuneForge is an MCP (Model Context Protocol) server that enables coding agents like Claude and Cursor to perform machine learning operations directly within chat interfaces, including dataset generati

We power 1M+ developers globally. Our researchers developed FlashAttention, Mixture of Agents, EinsteinArena, and more. Our platform is built for large-scale, latency-sensitive workloads on open-sourc

Chris Metinko / Axios: Collov Labs, whose visual interface lets users feed images and camera input into a model that AI agents can reason over and act on, raised a 23M Series A — Collov Labs, which tu

🚀Meet Carnice-V2-27b🚀 → Carnice is a 27 billion parameter model capable of beating models 10x the size in Hermes-agent, fully open-source and built on top of Qwen3.6-27B →Build to fit on Consumer GPU

arXiv:2604.21131v1 Announce Type: cross Abstract: AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips p

GPT-5.5 and GPT-5.5 Pro are now available in Hermes Agent through the Nous Portal and OpenRouter providers! (alongside the direct openai oauth provider from yesterday) GPT-5.5 and GPT-5.5 Pro are now

GPT-5.5 is a giant leap forward for handling ambiguity compared to previous GPT models. As Windsurf 2.0 focuses more on parallel agents, this model is key for long-horizon tasks — it excels at underst

GPT-5.5 now available in Deep Agents! GPT-5.5 is now available in the API. The model brings higher intelligence and stronger token efficiency to complex work, helping tasks get done with fewer retries

arXiv:2604.20911v1 Announce Type: cross Abstract: LLM agents deployed in production operate under operator-defined behavioral policies (system-prompt instructions such as prohibitions on credential di

arXiv:2310.02635v5 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is a promising approach for solving robotic manipulation tasks. However, it is challenging to apply the RL algorit

This is where we are right now. And i’m not gonna lie it feels pretty magical 🧚‍♀️ Qwen3.6 27B running inside of Pi coding agent via Llama.cpp on the MacBook Pro For non-trivial tasks on the @huggingf

arXiv:2604.19767v1 Announce Type: cross Abstract: We evaluate speculative decoding with EAGLE3 as an inference-time optimization for PayPal's Commerce Agent, powered by a fine-tuned llama3.1-nemotron-

Earth Day at #GoogleCloudNext, I’m demoing a Sustainability Agent at the @nvidia booth. Built with @Google ADK, @googlegemma, #nemotron, Cloud Run, @milvusio , @LangChain & @ollama to reason across im

arXiv:2604.20728v1 Announce Type: new Abstract: Autonomous systems that rely on learned perception can make unsafe decisions when sensor readings are misclassified. We study shielding for this setting

Introducing GPT-5.5 A new class of intelligence for real work and powering agents, built to understand complex goals, use tools, check its work, and carry more tasks through to completion. It marks a

Madison Mills / Axios: OpenAI says GPT-5.5's improvements are strongest in agentic coding, computer use, and early scientific research, which require reasoning across longer contexts — OpenAI on Thurs

arXiv:2604.19907v1 Announce Type: new Abstract: Recent agentic frameworks for 3D scene synthesis have advanced realism and diversity by integrating heterogeneous generation and editing tools. These to

arXiv:2604.19971v1 Announce Type: cross Abstract: Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can auto

arXiv:2604.18589v1 Announce Type: cross Abstract: Thematic analysis is difficult to scale: manual workflows are labor-intensive, while fully automated pipelines often lack controllability and transpar

Michele Catasta (@pirroh) at Google Cloud Next talking about what's new with Gemini, agentic applications, and what's next for builders. Fresh off Replit being named Google Cloud Partner of the Year.

New in Claude Code: /ultrareview (research preview) runs a fleet of bug-hunting agents in the cloud. Findings land in the CLI or Desktop automatically. Run it before merging critical changes—auth, dat

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/

T. K. Lin / KrASIA: Tencent launches an international beta for QClaw, its OpenClaw-based AI agent, and says the Chinese version, launched in March, reached over 1M users in 10 days — OpenClaw's founde

arXiv:2604.19064v1 Announce Type: new Abstract: In vision-and-language navigation (VLN), self-improvement from policy-induced experience, using only standard VLN action supervision, critically depends

arXiv:2509.16343v2 Announce Type: replace-cross Abstract: Building robust vision systems for high-stakes domains such as remote sensing requires stronger visual reasoning than what single-pass inferen

We need open traces so that everyone can train open agent models! cc @steipete @badlogicgames @thdxr @matanSF @hwchase17 People are misreading the SpaceX/Cursor deal as an M&A story. It’s actually a b

Google announced Ironwood, its seventh-generation TPU that is twice as power efficient as the previous generation, alongside specialized hardware designed to support the emerging agentic AI era. Ironw

arXiv:2604.16335v1 Announce Type: new Abstract: Despite recent progress in Large Language Model (LLM) Agents for Software Engineering (SWE) tasks, end-to-end fine-tuning typically relies on verifiable

arXiv:2511.12676v2 Announce Type: replace Abstract: Deploying embodied agents that can answer questions about their surroundings in realistic real-world settings remains difficult, partly due to the s

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

Friendly Machines is happening next Tuesday! We’re exploring how Hermes by @NousResearch and Claude are used to build useful agents: – live demos – Q&A with @NousResearch team – discuss your workflows