Knowledge catalogue
If you're an AI/agent builder, it's so important that you don't overbuild and overcommit on a specific toolset and infrastructure. Frontier labs are shipping not just the models, but the harnesses and
My comment on Devtools must be open source (exe.dev) — Hacker News.One of the arguments for open source software for end-users has always been the freedom to examine and modify how that software works
A coding agent finishes a change and wants to open a GitHub issue with a link to its results. The agent can describe the issue, but creating it belongs to a different system. It needs a tool that can
arXiv:2608.02650v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks. However, reliable tool-use planning remains
arXiv:2608.03468v1 Announce Type: new Abstract: Historical tool-use trajectories provide valuable experience for large language model (LLM) agents to plan and coordinate tool usage. Existing approache
DigitalOcean launched Kimi K3 on day 0. It’s already one of the most popular models on the platform and across the market: second most likes on Hugging Face, sixth most traffic on OpenCode. Getting a
Executive Summary Since our February 2026 report on AI-related threat activity, Google Threat Intelligence Group (GTIG) has continued to track a maturing transition from nascent AI-enabled operations
arXiv:2605.07103v1 Announce Type: new Abstract: Reaction feasibility prediction, as a fundamental problem in computational chemistry, has benefited from diverse tools enabled by recent advances in art
arXiv:2602.21265v2 Announce Type: replace Abstract: We introduce ToolMATH, a math-grounded diagnostic benchmark for evaluating long-horizon tool use under controllable tool-catalog conditions. ToolMAT
arXiv:2605.17453v1 Announce Type: cross Abstract: Tool-using LLM agents increasingly rely on external tools to make consequential decisions, yet most existing agent-security benchmarks and defenses im
Earlier this month I hosted a fireside chat session at the AI Engineer World's Fair with Cat Wu and Thariq Shihipar from Anthropic's Claude Code team. We talked about Claude Code, Claude Tag, Fable, c
arXiv:2608.10037v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical groundin
Following a successful private preview, we’re thrilled to open DigitalOcean Managed Agents to everyone. Teams can now deploy their preferred agent harness (like OpenCode, Codex CLI) or bring their own
arXiv:2609.01736v1 Announce Type: cross Abstract: Large language models (LLMs) augmented with external tools have demonstrated remarkable capability in solving complex real-world tasks. However, exist
arXiv:2605.09931v1 Announce Type: cross Abstract: Tool-integrated reasoning (TIR) enables large language models (LLMs) to enhance their capabilities by interacting with external tools, such as code in
arXiv:2608.23992v1 Announce Type: cross Abstract: Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond pretrained knowledge. The Model Context Protoco
arXiv:2608.24368v1 Announce Type: new Abstract: Reliable multi-turn tool use requires an agent to preserve an evolving task state and ensure that each action remains consistent with it. However, direc
arXiv:2608.23635v1 Announce Type: cross Abstract: Large language models (LLMs) rely on tool calling as a fundamental agent capability, enabling them to invoke external systems and complete tasks beyon
arXiv:2608.24571v1 Announce Type: new Abstract: Tool-augmented language models are bounded by the APIs humans bothered to write; existing tool-creation systems patch this by prompting a frozen LLM at
arXiv:2605.26691v1 Announce Type: new Abstract: Medical AI agents increasingly use external tools for diagnosis, treatment recommendation, and evidence retrieval, yet most existing approaches assume t
arXiv:2608.22708v1 Announce Type: new Abstract: Tool use in LLM systems faces a structural trade-off. Progressive disclosure keeps the prompt small by showing only the tools relevant to the current ta
With hopes of a Qwen3.8-35B-A3B release now mostly dashed, many people including myself are looking at fine-tunes and other variants of Qwen3.6-35B-A3B to run on VRAM-limited hardware. I decided to tr
I didn't have early access to today's Claude Fable 5 release, but I've spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It's slow,
arXiv:2606.07904v1 Announce Type: new Abstract: Tool-augmented large language model agents increasingly rely on external APIs, but standard tool schemas describe how to call a tool, not when the tool
arXiv:2605.14038v1 Announce Type: new Abstract: Large language models (LLMs) increasingly act as autonomous agents that must decide when to answer directly vs. when to invoke external tools. Prior wor
arXiv:2605.13228v1 Announce Type: cross Abstract: Video understanding requires active evidence seeking, motivating tool-augmented video agents for temporal reasoning, cross-modal understanding, and co
arXiv:2604.14951v1 Announce Type: cross Abstract: Tool learning with foundation models aims to endow AI systems with the ability to invoke external resources -- such as APIs, computational utilities,
GLM-5.1 Tool Calling Issue Fix & Chat Template Update If you are running GLM-5.1 with vLLM/SGLang and using tool calling, please update your chat template. http://huggingface.co/zai-org/GLM-5.1/blob/m
arXiv:2604.13787v1 Announce Type: new Abstract: Large Language Models (LLMs) enhance their problem-solving capability by utilizing external tools. However, in open-world scenarios with massive and evo
arXiv:2606.25819v1 Announce Type: new Abstract: Large language models are increasingly deployed as agents that solve tasks by interacting with external tool environments. Although recent tool-use benc
arXiv:2605.20342v1 Announce Type: new Abstract: Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promisin
arXiv:2604.11322v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated impressive capabilities in utilizing external tools. In practice, however, LLMs are often exposed to to
arXiv:2604.10788v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools durin
// ContextLeak in AI Agents // The whole attack surface here is a tool name and a tool description. Stealing an LLM agent's runtime context, meaning the user prompt, the execution trajectory and the t
// The Bitter Lesson of Tool Calling // Tool calling is a design choice, and the defaults are quietly costing accuracy. How so? New research releases a generation-spanning comparison of programmatic t
arXiv:2602.01334v2 Announce Type: replace Abstract: Vision tool-use reinforcement learning (RL) can equip vision language models with visual operators such as crop-and-zoom and achieves strong perform
arXiv:2602.20426v2 Announce Type: replace Abstract: While most efforts to improve LLM-based tool-using agents focus on the agent itself - through larger models, better prompting, or fine-tuning - agen
New in LangSmith Fleet: Tool access controls and usage tracking. 📊 Track cost and usage by user, agent, and tool from a single dashboard 💳 Set spend limits per user or team to prevent surprises ✅ Cont
arXiv:2609.15397v1 Announce Type: new Abstract: AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative executio
arXiv:2609.09395v1 Announce Type: new Abstract: Language models act through tools, yet practical agents face libraries containing thousands of interfaces. We introduce the tool menu as the short, orde
Enterprise agent adoption isn’t one-size-fits-all. While many teams will opt for managed commercial platforms, such as Gemini Enterprise Agent Platform for turnkey agent deployment and governance, dev
arXiv:2609.00967v1 Announce Type: new Abstract: As large language models increasingly act through external tools, deciding when to call a tool has become a central problem alongside deciding how to us
arXiv:2606.06284v1 Announce Type: new Abstract: Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool ca
arXiv:2604.19821v1 Announce Type: new Abstract: Large language model (LLM) agents augmented with external tools often struggle as number of tools grow large and become domain-specific. In such setting
arXiv:2607.04686v1 Announce Type: cross Abstract: Tool calling is central to modern language model agents, but aggregate benchmark scores often hide where tool use fails. A model that never calls a ne
arXiv:2609.18849v1 Announce Type: cross Abstract: An agentic request spends substantial wall-clock time waiting for tools, and its KV cache holds GPU memory the whole time. Serving systems decide whet
arXiv:2609.03493v1 Announce Type: new Abstract: Modern vision-language models (VLMs) can directly answer many image-grounded questions, yet they often struggle with complex queries requiring fine-grai
arXiv:2609.16268v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly interleave natural language reasoning with external tools such as web search and code execution. These to
arXiv:2601.12449v2 Announce Type: replace-cross Abstract: AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper to
arXiv:2606.02357v1 Announce Type: cross Abstract: Tool-augmented multimodal agents show strong benchmark gains, often taken as evidence that agents have learned to use tools. We argue that this interp
arXiv:2609.30293v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) enables AI agents to discover and call tools, but loading every definition becomes expensive as connected catalogs gr
arXiv:2607.28225v1 Announce Type: new Abstract: Agentic vision-language models (VLMs), which interleave textual reasoning with explicit tool calls such as cropping and code-based image manipulation, h
arXiv:2605.12481v2 Announce Type: replace Abstract: Computer Use Agents (CUAs) can act through both atomic GUI actions, such as click and type, and high-level tool calls, such as API-based file operat
arXiv:2609.19425v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents fail in a way no tool-selection or tool-security method addresses: they call tools that do not exist an
arXiv:2608.26295v1 Announce Type: cross Abstract: Tool-augmented LLMs must arbitrate between two fallible sources when a tool return conflicts with their parametric memory, yet existing evaluations me
arXiv:2608.27146v1 Announce Type: new Abstract: Tool-augmented LLM agents must rely on untrusted runtime Observations to complete open-ended tasks; however, when tool outputs no longer merely provide
arXiv:2608.01056v1 Announce Type: cross Abstract: Tool-using language-model agents are governed not only by task prompts but also by persistent system-side instructions that specify tools, arguments,
arXiv:2512.21414v2 Announce Type: replace Abstract: Recent tool-use frameworks powered by vision-language models (VLMs) improve image understanding by grounding model predictions with specialized tool
arXiv:2511.10899v2 Announce Type: replace Abstract: Tool-augmented Language Models (TaLMs) can invoke external tools to solve problems beyond their parametric capacity. However, it remains unclear whe
Editor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your