Search: “tools”

arXiv:2602.14517v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved strong results in mathematical reasoning, and are increasingly deployed as tutoring and learning support

arXiv:2604.14877v1 Announce Type: new Abstract: Does reinforcement learning genuinely expand what LLM agents can do, or merely make them more reliable? For static reasoning, recent work answers the se

arXiv:2604.05541v2 Announce Type: replace Abstract: Reliable interpretation of echocardiography (Echo) is crucial for assessing cardiac function, which demands clinicians to synchronously orchestrate

Fastest way to deploy deepagents gets even more powerful we just shipped support for subagents with `deepagents deploy`! add an agents/ dir to your project with an AGENTS.md per specialized subagent.

arXiv:2604.15037v1 Announce Type: cross Abstract: Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, multimodal interaction. However, existi

arXiv:2603.01410v2 Announce Type: replace Abstract: Knowledge graphs provide structured and reliable information for many real-world applications, motivating increasing interest in combining large lan

Hermes creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. D

arXiv:2604.14159v1 Announce Type: new Abstract: Mobile input method editors (IMEs) are the primary interface for text input, yet they remain constrained to manual typing and struggle to produce person

arXiv:2604.14240v1 Announce Type: cross Abstract: The simulation of complex systems increasingly relies on sophisticated but fundamentally opaque computational black-box simulators. Surrogate models p

The Agent Readiness score can help site owners understand how well their websites support AI agents. Here we explore new standards, share Radar data, and detail how we made Cloudflare’s docs the most

Nicholas Moore, who pleaded guilty to hacking the U.S. Supreme Court's electronic document filing system dozens of times over several months, was sentenced on Friday to a year of probation. Moore also

arXiv:2509.06477v2 Announce Type: replace Abstract: Shortcuts such as APIs and deep-links have emerged as efficient complements to flexible GUI operations, fostering a promising hybrid paradigm for ML

NanoCo, the startup behind NanoClaw, a fast-growing alternative to OpenAI Group PBC’s OpenClaw project, said today it’s teaming up with Vercel Inc. and OneCLI to try to fix the “trust problem” holding

Ollama version 0.21 added support for Hermes Agent, a self-improving AI agent developed by Nous Research. This release enables users to run Hermes Agent through the Ollama platform, expanding its capa

Q-Day—the moment when quantum computers can break widely used cryptography—may be approaching faster than expected due to recent algorithmic and hardware advances. Advances in algorithms and design ar

arXiv:2604.13757v1 Announce Type: new Abstract: The next generation of autonomous AI systems will be constrained not only by model capability, but by how intelligence is structured across heterogeneou

arXiv:2604.14656v1 Announce Type: cross Abstract: Most medical multimodal benchmarks focus on static tasks such as image question answering, report generation, and plain-language rewriting. Patient ed

arXiv:2604.14399v1 Announce Type: new Abstract: Autonomous on-orbit servicing demands embodied agents that perceive through visual sensors, reason about 3D spatial situations, and execute multi-phase

arXiv:2604.14363v1 Announce Type: new Abstract: Multimodal language models systematically underperform on visual perception tasks, yet the structure underlying this failure remains poorly understood.

Running LLMs across Cloudflare’s network requires us to be smarter and more efficient about GPU memory bandwidth. That’s why we developed Unweight, a lossless inference-time compression system that ac

arXiv:2604.03307v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success, yet they remain prone to perception-related hallucinations in fine-graine

we just shipped support for subagents with `deepagents deploy`! add an agents/ dir to your project with an AGENTS.md per specialized subagent. subagents are great for task delegation with isolated/opt

what should we ship next in `deepagents deploy`? we just shipped support for subagents with `deepagents deploy`! add an agents/ dir to your project with an AGENTS.md per specialized subagent. subagent

🇺🇸 xAI just dropped a real-time speech-to-text model built for voice apps: high limits, multi-language support, the works. Priced at just 0.10–0.20/hour, crushing most competitors. Quiet release, loud

arXiv:2504.15801v2 Announce Type: replace Abstract: As large language models (LLMs) and LLM-based agents increasingly interact with humans in decision-making contexts, understanding the trust dynamics

arXiv:2507.01976v2 Announce Type: replace-cross Abstract: Synthetic network traffic generation has emerged as a promising alternative for various data-driven applications in the networking domain. It

arXiv:2604.13346v1 Announce Type: new Abstract: Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reaso

Antioch Inc., a developer of cloud-based simulation software for artificial intelligence-enabled robots, has raised 8.5 million in funding to accelerate the development of more autonomous systems outs

Visual communication platform provider Canva Pty Ltd. today unveiled Canva AI 2.0, an overhaul of its platform that offers a conversational, agentic system aimed at becoming the place where teams star

Radio-frequency identification devices and software company Impinj Inc. today announced an upgrade of its R700 RAIN RFID reader with a more powerful processor and expanded memory to help enterprises b

arXiv:2604.13201v1 Announce Type: new Abstract: Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging. Benchmarks

Lua Global Inc. today announced it raised 5.8 million in early-stage funding to build a platform that allows any team, irrespective of its technical depth, to build, deploy and manage an agentic artif

arXiv:2512.06695v2 Announce Type: replace Abstract: Quantum generative models exploit quantum superposition and entanglement to enhance learning efficiency for both classical and quantum data. Recentl

arXiv:2604.13345v1 Announce Type: new Abstract: The paper presents design and prototype implementation of an edge based object detection system within the new paradigm of AI agents orchestration. It g

NEW Research from Google. Integration test failures are painful because the signal is buried in messy logs. Massive output, heterogeneous systems, low signal-to-noise ratio, and unclear root causes. T

China successfully tested an advanced device capable of cutting underwater structures like submarine cables at depths of 3,500 meters , raising global security concerns. Since more than 95% of global

Solidroad Inc., a startup that develops software for use in training and coaching customer service agents, today said it has raised 25 million in an early-stage funding. The Series A round, led by U.K

Rina Chandran / Rest of World: Voice actors worldwide are mobilizing to protect their livelihoods and personality rights as Hollywood studios push AI dubbing to replace human performances — Voice AI t

arXiv:2604.13318v1 Announce Type: cross Abstract: Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with lon

An experimental voice pipeline for the Agents SDK enables real-time voice interactions over WebSockets. Developers can now build agents with continuous STT and TTS in just ~30 lines of server-side cod

arXiv:2604.12513v1 Announce Type: new Abstract: We study whether a variational language model can support a minimal and measurable form of agentic control grounded in its own internal evidence. Our mo

arXiv:2604.12999v1 Announce Type: new Abstract: We introduce HypoExplore, an agentic framework that formulates neural architecture discovery for visual recognition as a hypothesis-driven scientific in

arXiv:2604.12421v1 Announce Type: new Abstract: Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large l

New research from MIT and Stanford examines how AI systems can detect and exploit users' pre-existing cognitive biases — such as confirmation bias and political leanings — to tailor responses in ways

Vultr offers preemptible cloud instances powered by AMD Instinct GPUs, providing a cost-effective option for running GPU-accelerated workloads such as AI/ML training, inference, and high-performance c

Matt Burgess / Wired: Analysis: nearly 90 schools and 600 students globally have been impacted by AI-generated deepfake nudes; North America had nearly 30 reported cases since 2023 — An analysis by WI