Search: “tools”

we recently trimmed the deepagents harness base prompt by 65% (including tool info) it shows — deepagents is cheap! We ran DeepSeek V4 Flash through 4 more agent harnesses (Hermes Agent, Pi Agent, Pri

arXiv:2608.04240v1 Announce Type: cross Abstract: Superhuman game engines in domains like chess have made expert-level evaluations easily accessible, yet they communicate what is true without the natu

this is a really clean and unique ai tool that acts more like an extension of you took me 15 min to set up a custom ai voice assistant w/ it’s own # that also picks up my calls when my phone is off an

Together AI gives developers a high-throughput production path for running DeepSeek V4 Flash across coding, tool-use, and agentic workloads. Start building: https://www.together.ai/models/deepseek-v4-

arXiv:2607.29549v1 Announce Type: new Abstract: Large language models have demonstrated strong mathematical problem-solving capabilities, yet reliably verifying their candidate answers remains challen

OpenAI’s GPT‑Live can listen and speak simultaneously. The new voice stack routes audio through a dedicated fast path so that speech flows continuously while intensive reasoning and external tool call

arXiv:2607.29561v1 Announce Type: cross Abstract: Symbolic Regression (SR) aims to discover analytical equations from observational data and plays a central role in scientific modeling. While recent L

arXiv:2607.22868v1 Announce Type: new Abstract: Runtime guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable, what a judge observes, and whe

Nexus connects to the agentic harnesses your teams already use, whether that’s Claude Code, Codex, OpenCode, or your own custom tooling. It gives you: → Intelligent routing, automatically matching eac

Together gives developers an efficient, high-throughput production path for K3’s long, tool-heavy agent workloads, hosted on Together AI’s US-based infrastructure with zero data retention. Start build

arXiv:2508.21797v2 Announce Type: replace-cross Abstract: Industry 4.0's highly networked Machine Tool Controllers (MTCs) are prime targets for replay attacks that use outdated sensor data to manipula

arXiv:2607.19848v1 Announce Type: new Abstract: There is growing evidence that data diversity is crucial for developing fair and robust NLP models. However, current approaches to measure diversity rem

arXiv:2607.19356v1 Announce Type: new Abstract: Tool-using LLM agents increasingly execute high-impact actions, making runtime safety monitoring essential. We present NEXUS (Neural EXecution Utility a

arXiv:2607.13558v1 Announce Type: new Abstract: Urban region profiling constitutes a core problem in urban computing, supporting applications such as population estimation, economic assessment, and en

Just yesterday an engineer posted 'open swe is my favorite productivity tool at the moment' in slack Open source wins! Sierra isn't the first to build this - Ramp, Stripe, CoinBase also have If you wa

Notes on GPT-5.6, which includes some interesting new additions to the API (programmatic tool calling and multi-agent in particular) - plus 18 pelicans for the 6 reasoning levels and 3 new models: htt

Popular open source AI developer tool Ollama raises $65M, grows to nearly 9M users https://techcrunch.com/2026/07/09/popular-open-source-ai-developer-tool-ollama-raises-65m-grows-to-nearly-9m-users/?u

The model has an advisor tool that natively escalates to a stronger model when needed. This model is hosted in the U.S. by Perplexity on Nvidia B200 GPUs. We will improve the model in research preview

We built a plugin that traces every Claude Code session straight into LangSmith. Three commands, one JSON block, and every message, tool call, and subagent run shows up as an inspectable trace. Setup

Grok will be able to call Imagine as a tool in agentic mode for image/video generation. As Imagine keeps improving, this will be amazing for game developers! I got to try Grok 4.5 in early access in C

arXiv:2607.04395v1 Announce Type: new Abstract: Recent agentic approaches to LLM-based kernel generation have achieved impressive results on CUDA. For emerging AI accelerators such as AWS Trainium and

arXiv:2607.02927v1 Announce Type: cross Abstract: Video understanding is moving beyond closed-context perception toward open-world evidence exploration, a paradigm formalized as Video Deep Research (V

We released our in-house Japanese, English, and Chinese translation tool, Sakana Translate! Try it→ https://translate.sakana.ai 🐟 • Translate: Handles long text in real time • Proofread: Tone and phra

The Top AI Papers of the Week (June 28 - July 5): - RLMF - AutoMem - Paper Assistant Tool - MCP Server Patterns - The Verification Horizon - Red Queen Gödel Machine - Generative Skill Composition Read

I never touched any tool or anything, all designs & prompts were the AI's choices. I pushed back a couple times: 'Are there ways to make the whole thing better - it is lots of static images and such?

i'm open sourcing UNBROKER: a tool that finds where your personal info is exposed by data brokers and files the removals for you it runs as a skill in Hermes Agent _________ your data is everywhere; h

So i built LangGraph Sync. it’s an interactive web tool that visualizes langgraph workflows & lets you edit & bidirectionally synchronize the graph & code in real time. you edit the visual graph, your

Fugu is now available on OpenCode! ✨ When our team was developing Fugu’s multi-agent orchestration, OpenCode was our tool of choice to verify our models. We share a core philosophy with the OpenCode t

arXiv:2607.01000v1 Announce Type: new Abstract: Recent research has increasingly focused on understanding how Transformers store and process knowledge, as well as how this knowledge can be edited. Res

Joseph Cox / 404 Media: A researcher says a vulnerability in Apple's Hide My Email tool lets anyone see a user's real email address; first reported in June 2025, Apple has not fixed it — “Hide My Emai

arXiv:2605.11030v2 Announce Type: replace-cross Abstract: Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often con

Build a in-browser debug mode sort of tool for @LangChain deepagents that resides a shortcut away. Helpful to debug there and then as the conversation is going on without switching tabs, like seeing a

do you know what you pay for in agentic workloads? cached tokens! session with 50+ tool calls -> prompt is billed 50 times all providers give 1/5 cached discount for GLM-5.2 we at @FireworksAI_HQ drop

arXiv:2606.31648v1 Announce Type: new Abstract: We present LuckyStar 111B, a 111B-parameter hybrid reasoning model developed through a collaboration between Cohere and LG CNS for Korean-English enterp

arXiv:2606.29073v1 Announce Type: cross Abstract: Model Context Protocol (MCP)-style ecosystems give language-model applications a practical connection layer for tools, resources, prompts, and transpo

I've added video support to my 'shot-scraper' browser automation tool - you (or your coding agent) can now create a storyboard YAML file and use that to record a video demo of new web application feat

Tutorial on using Gemini live to build a voice agent Uses deepagents as a tool: offload complex work to this subagent, use Gemini live for the naturalness/latency Building voice agents can come with t

Deep Agents now supports dynamic subagents. Instead of invoking subagents with tool calls, the main agent writes orchestration code to coordinate work at scale. This enables workflows like processing

LiteParse is unreasonably good for document parsing ✅ It is the fastest document parsing tool out there - average parse time per page is 3ms ⚡️⚡️ ✅ Now that we support markdown, it tops opendataloader

arXiv:2606.26346v1 Announce Type: new Abstract: Agentic benchmarks have emerged across general-purpose and domain-specific settings, including finance, coding, law, and drug discovery, yet energy-doma

Jo Constantz / Bloomberg: California launches a tool to serve as an “early warning system” for widespread AI-driven job loss, linking AI exposure with unemployment insurance claims — Politicians like

Your Hermes Agent can now adopt an animated pet: a small sprite that reacts to what the agent is doing (idle, running a tool, thinking, waiting, finishing, failing) in the GUI or TUI. You have nearly

A Biden-appointed activist judge, Sparkle Sooknanan, just blocked a commonsense tool to keep non-citizens from voting. The SAVE system simply encourages states to work with DHS to check their voter ro

Model council as a tool to push performance definitely works, I think the interesting next frontier is trying to scale this at the agent level have been thinking a bunch about model routing and relate

Built a super fast PDF parsing service with LiteParse! LiteParse is a standalone OSS PDF parsing tool by @llama_index focused exclusively on fast and lightweight parsing. Building it was fun. @cursor_

arXiv:2606.11425v1 Announce Type: cross Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: ha