Search: “tools”

arXiv:2508.15754v2 Announce Type: replace-cross Abstract: Tool use is often assumed to monotonically improve reasoning, where external evidence is expected to help when relevant and be ignored when ir

arXiv:2606.28960v1 Announce Type: new Abstract: Physicians now pose millions of clinical questions to AI tools each week, yet these tools are evaluated largely on hypothetical or exam-style questions,

arXiv:2606.03907v1 Announce Type: cross Abstract: Agentic AI coding tools write code with increasing autonomy and in doing so decide when to import a library and when to implement functionality from s

arXiv:2506.00886v3 Announce Type: replace Abstract: As large language models evolve into tool-augmented agents, a central question remains unresolved: when is external tool use actually justified? Exi

arXiv:2609.39018v1 Announce Type: cross Abstract: Frontier models can control robots, but reasoning through every reach, grasp, and retreat makes manipulation slow and token-intensive. We revisit code

Giving an assistant extra tools seems harmless. Surprisingly, this paper shows it can make the assistant stop answering questions it knows. Across six models, the answer rate on questions that need no

arXiv:2607.11818v2 Announce Type: replace-cross Abstract: We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful

arXiv:2608.00326v2 Announce Type: replace Abstract: Tool calling allows large language models (LLMs) to invoke external computation during problem solving, a useful capability in various fields includ

arXiv:2608.00847v1 Announce Type: new Abstract: Most current visual trackers adopt a matching-based architecture trained exclusively on tracking datasets, whose performance gains depend heavily on the

arXiv:2606.20728v1 Announce Type: new Abstract: Vision foundation tools such as open-vocabulary detectors, segmentation models, and post-processing operators are powerful building blocks for computer

Token costs are why there will be no saas apocalypse / good dev tools are cached intelligence for agents! The popular theory goes: agents can write code, so they'll just rebuild every tool from scratc

Uber Caps Usage of AI Tools Like Claude Code to Manage Costs I wrote the other day about Uber blowing its 2026 AI budget in four months, and how that wasn't particularly surprising given they would ha

arXiv:2512.16310v3 Announce Type: replace-cross Abstract: LLM-based agents increasingly use multiple external tools to complete complex tasks. We study Tools Orchestration Privacy Risk (TOP-R): an age

arXiv:2605.28876v1 Announce Type: cross Abstract: CI failure logs are large (median 5k lines, max 200k in this corpus) and noisy. Coding agents that try to debug them depend on an upstream tool to red

arXiv:2604.01532v2 Announce Type: replace Abstract: LLM agents are beginning to invoke industrial asset-management tools through the Model Context Protocol (MCP), yet whether they can act reliably on

arXiv:2605.10125v1 Announce Type: new Abstract: Artificial intelligence (AI) tools are being incorporated into scientific research workflows with the potential to enhance efficiency in tasks such as d

You can now use OpenAI OAuth to generate images with Hermes Agent! Update Hermes and use the ‘hermes tools’ command to configure the image generation tool to use OpenAI! Reminder: we have a $26,000 on

OpenAI's new Euphony tool works almost exactly the same way as my Codex transcript viewer https://tools.simonwillison.net/codex-timeline?url=https%3A%2F%2Fgist.githubusercontent.com%2Fsimonw%2Fa9eb599

arXiv:2604.11111v1 Announce Type: cross Abstract: The rapid adoption of AI tools such as ChatGPT has significantly transformed academic practices, offering considerable benefits for both students and

Explore the top AI papers of the week with our brand-new MCP tools. Connect it to Codex, Claude Code, or Grok Bot. Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to

arXiv:2610.00613v1 Announce Type: new Abstract: Large language model (LLM) based agents are often criticized for lacking spatial understanding and mainly exploiting statistical text patterns. We inves

arXiv:2608.07446v1 Announce Type: cross Abstract: Rapid adoption of large language models (LLMs) in enterprise settings has introduced operational, security, and governance risks. As generative AI app

good dev tools are cached intelligence for agents! Token costs are why there will be no saas apocalypse / good dev tools are cached intelligence for agents! The popular theory goes: agents can write c

arXiv:2605.14241v1 Announce Type: new Abstract: Tool-augmented LLM agents increasingly access the same tool type through multiple functionally equivalent providers, such as web-search APIs, retrievers

arXiv:2502.11271v2 Announce Type: replace-cross Abstract: Solving complex reasoning tasks may involve visual understanding, domain knowledge retrieval, numerical calculation, and multi-step reasoning.

the most important abstraction in AI agents isnt the model — its the harness it orchestrates tools, memory, prompts. this is where all the alpha is deepagents is our take: built-in tools, memory, smar

arXiv:2610.05031v2 Announce Type: replace Abstract: Large language models are increasingly used as integration layers above specialized tools, but a stronger component does not necessarily produce a s

arXiv:2610.00313v1 Announce Type: new Abstract: Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise. Rules to

Maria Deutscher / SiliconANGLE: Firecrawl, which provides web scraping tools for AI agents, raised a 75M Series B led by Smash Capital — Firecrawl Inc., a provider of web scraping tools for artificial

arXiv:2609.22218v1 Announce Type: cross Abstract: As LLM agents are exposed to hundreds to tens of thousands of skills, tools, and API functions, full-library prompting becomes costly, slow, and less

AI tools have given us a lot of slop research, but I'm not talking about that. I'm talking about real productivity acceleration due to AI tools (E.g. iterating ideas that would've taken multiple days

arXiv:2608.29309v1 Announce Type: cross Abstract: This work provides an overview of the different strategies that can be used to evaluate the performance of AI models and agents based on large languag

arXiv:2607.27703v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task

This wins the prize for sleazy misrepresentation. @mattShumer took my 2023 argument for hybridizing LLMs with symbolic tools – which is *exactly* what everyone does nowadays – and made it sound like I

Many AI tools rent intelligence. Kimi K3 on Fireworks is different. Fine-tune it on your own data, serve from US-hosted endpoints, and own the weights. Zero data retention. ICYMI yesterday, start buil

arXiv:2607.17075v2 Announce Type: replace-cross Abstract: The advent of LLMs has significantly changed the research on privacy policy and data compliance analysis by enabling tasks that previously req

Open models are not just a pricing story. They are what happens when the AI stack becomes modular: models, APIs, harnesses, tools, and inference all improving independently. Together AI is building th

Introducing Computer for Counsel. Computer now connects the research databases, document tools, and matter-management systems lawyers use every day. Pull citable sources from @midpageAI, @LegalZoom, @

This article describes Hugging Face's automated weekly release process for the huggingface_hub library, which combines AI-assisted tools with human oversight to streamline software deployment. The app

arXiv:2606.05806v1 Announce Type: new Abstract: Existing benchmarks evaluate Tool-Integrated Reasoning (TIR) in LLMs on idealized ''happy paths'', largely overlooking real-world tool failures. We intr

Cursor has launched a feature enabling users to publish and share canvases—custom applications such as dashboards, reports, and internal tools—with their teams. This update extends Cursor's canvas fun

Announcing our new collaboration with @Microsoft Organizations can now build internal tools, workflows, or data dashboards in Replit and publish directly to Microsoft Fabric with security, authenticat

Vercel has expanded its Chat SDK to incorporate AI SDK tools, enabling developers to build conversational applications with enhanced AI capabilities. This integration likely allows developers to lever

Sneaky interventions, interactive installations, tools built for other artists to use. @kcimc's practice lives where machine learning, computer vision, and social technology collide. See his new inter

arXiv:2605.07339v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks. However, existing methods rely on a s

This post from Swyx (a prominent figure in AI/developer experience circles) comments on Bloomberg's sudden media interest in developer experience and AI coding tools, suggesting this topic has become