Knowledge catalogue
Co-authors:Stenal Jolly, Strategic Cloud Engineer, GoogleAnubhav Dhawan, Software Engineer, Google Following the landmark announcement of MCP Toolbox v1.0, we're thrilled to announce that the MCP Tool
arXiv:2610.04836v1 Announce Type: new Abstract: Remote sensing agents rely on perception, measurement, and raster analysis tools to solve Earth observation tasks. We refer to their judgments and quant
arXiv:2610.03213v1 Announce Type: new Abstract: Tool-equipped AI agents use tool calls to access data and act on external systems. Horizontal growth of agentic systems increases the number of these in
arXiv:2610.02330v1 Announce Type: new Abstract: Large language models (LLMs) rely on long-horizon tool invocation sequences for complex tasks, where each invocation can alter the task state and condit
arXiv:2609.37315v1 Announce Type: cross Abstract: Tool-using agents are entering settings where a wrong action carries real cost, and the benchmarks certifying them grade what each simulated tool call
arXiv:2508.14925v2 Announce Type: replace-cross Abstract: By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a c
arXiv:2608.14047v1 Announce Type: cross Abstract: This paper integrates end-to-end Visual-Language-Action (VLA) models with agentic tool-use to propose Agentic Robot with Tool-use (ART). ART is a tool
arXiv:2607.11183v2 Announce Type: replace Abstract: Large language models increasingly operate as tool-using agents, where small format, argument, or function-call errors can invalidate otherwise plau
Samantha Kelly / Bloomberg: The US FDA drops an enforcement complaint against Whoop over its blood pressure tracking tool, reversing a July 2025 warning letter; Whoop is updating the tool — The US Foo
arXiv:2605.18500v1 Announce Type: new Abstract: Large language models (LLMs) have increasingly leveraged tool invocation to enhance their reasoning capabilities. However, existing approaches typically
arXiv:2605.17774v1 Announce Type: new Abstract: Large language models are increasingly used as planning components in agentic systems, but current tool-use pipelines often require full tool schemas to
arXiv:2605.09934v1 Announce Type: new Abstract: Multimodal large language models increasingly solve vision-centric tasks by calling external tools for visual inspection, OCR, retrieval, calculation, a
Rachel Metz / Bloomberg: Anthropic announces 12 Claude plugins for the legal sector, including a “commercial counsel” tool for reviewing vendor agreements and a bar exam study tool — Anthropic PBC is
Accessing enterprise data is shifting from static reports to dynamic use by autonomous systems. To keep up, organizations must route fragmented data from SaaS, IoT, and legacy sources into secure, sca
arXiv:2605.11928v2 Announce Type: replace Abstract: Tool-use language agents are evaluated on benchmarks that assume clean inputs, unambiguous tool registries, and reliable APIs. Real deployments viol
arXiv:2610.13330v1 Announce Type: new Abstract: Designing tool-integrated reasoning agent systems for complex chemical tasks remains a fundamental challenge. Although recent chemical agents have demon
Introducing Auto Review for tool requests Bionic uses AST parsing, command matching, and a reviewer subagent to auto-approve shell tool requests In our team's internal use, ~82% of commands are approv
arXiv:2608.26189v1 Announce Type: new Abstract: Tool-using agents fail two ways: choosing the wrong tool, or forming wrong arguments, and an early failure of either kind can silently corrupt everythin
arXiv:2608.06370v1 Announce Type: new Abstract: Tool use transforms LLMs into agents that act beyond their training data, and for code-capable models, programmatic tool calling extends this further by
arXiv:2608.02372v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in task-oriented dialogue systems that support multi-step decision-making in high-stakes domains
arXiv:2608.02217v1 Announce Type: new Abstract: Agentic multimodal reasoning extends passive image understanding by allowing VLMs to actively acquire and refine visual evidence through visual tool int
Nous Research announced an enhancement to their Hermes AI model where terminal tool calls will now be displayed in formatted markdown codeblocks when the display tool calls feature is enabled. This im
arXiv:2606.00096v1 Announce Type: cross Abstract: Visual agents employ external visual tools within visual chains of thought to incorporate fine-grained evidence. While prior work has mainly studied t
arXiv:2606.02132v1 Announce Type: new Abstract: Agentic reinforcement learning can induce tool abuse, where models overuse external tools even for queries solvable by internal reasoning. Existing appr
arXiv:2605.07990v1 Announce Type: cross Abstract: When a tool-calling agent picks the wrong tool, the failure is invisible until execution: the email gets sent, the meeting gets missed. Probing 12 ins
I'm really excited about this as a new tool in our interpretability tool kit In a new paper, we present NLAs, an unsupervised method for converting an LLM's internal state into human-readable text. I'
arXiv:2512.17052v4 Announce Type: replace Abstract: Function calling agents powered by Large Language Models (LLMs) select external tools to automate complex tasks. On-device agents typically use a re
arXiv:2604.15715v1 Announce Type: cross Abstract: The development of general-purpose agents requires a shift from executing simple instructions to completing complex, real-world productivity workflows
I prefer my design tool to be more closely integrated with where my agents work. I spent a few hours building my own design tool (inspired by Claude Design) inside my orchestrator. I can use this with
arXiv:2609.26836v1 Announce Type: new Abstract: Agentic AI systems are increasingly adopting automated pipelines that integrate multiple tools. While prior research and benchmarks have studied about t
arXiv:2609.25678v1 Announce Type: cross Abstract: Large language model (LLM) agents must generalize from tools seen during training to unseen tools at deployment. A key challenge is tool trialing, i.e
arXiv:2609.11999v1 Announce Type: cross Abstract: In this study, we examine whether a general shell can outperform specialized tools on enterprise tasks. Shell-based agents have shown strong results i
arXiv:2608.29397v1 Announce Type: new Abstract: Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is
arXiv:2608.29363v1 Announce Type: new Abstract: Enterprise data agents answer business queries by chaining many tool calls over multiple reasoning steps, routinely accumulating hundreds of thousands o
arXiv:2608.29942v1 Announce Type: cross Abstract: The key limitation of current state-of-the-art influence-based guardrails is that they do not reliably distinguish a legitimate, user-authorized actio
arXiv:2608.10042v1 Announce Type: cross Abstract: Tool-use LLMs are increasingly asked to act on users' behalf, but existing benchmarks usually focus on profile recall, style imitation, generic tool u
arXiv:2608.08557v1 Announce Type: new Abstract: Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing
arXiv:2607.05790v1 Announce Type: new Abstract: Tool-augmented large language models extend their capabilities beyond parametric knowledge through external tools, but tend to invoke them unnecessarily
arXiv:2606.20023v2 Announce Type: replace-cross Abstract: As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, pri
arXiv:2606.06566v1 Announce Type: cross Abstract: Agentic tool-calling language models depend on large registries of callable APIs, functions, and local actions. Placing full tool specifications direc
arXiv:2605.29561v1 Announce Type: new Abstract: Tool calling extends large language models (LLMs) by enabling grounded interaction with external executable interfaces, thereby supporting environment-c
arXiv:2604.06205v1 Announce Type: cross Abstract: The growth of online platforms and user content requires strong content moderation systems that can handle complex inputs from various media types. Wh
A developer expressed enthusiasm for the emerging convergence of `AGENTS.md`, agent skills (SKILL.md), and tool configuration toward portable, cross-tool interfaces rather than siloed, tool-specifi...
arXiv:2610.07086v1 Announce Type: cross Abstract: LLM agents interact with external systems by generating structured tool calls. Given a user request, conversational context, and a catalog of tool sch
arXiv:2609.06124v1 Announce Type: new Abstract: High-quality multi-turn tool-use data is essential for training agentic models, yet existing data synthesis methods often underrepresent the argument-le
arXiv:2609.06792v1 Announce Type: new Abstract: Android agents using a hybrid action space that combines GUI actions and tool actions (e.g., accessing application data via APIs) remain largely underex
arXiv:2609.02751v1 Announce Type: new Abstract: As generative AI tools become increasingly powerful and easy to use, people can easily edit portrait images with a prompt, necessitating the task of ima
arXiv:2609.00949v1 Announce Type: cross Abstract: Multi-turn tool calling is a core evaluation scenario for large language model (LLM) agents. On public tool-calling benchmarks, open-weight models now
arXiv:2608.18171v1 Announce Type: new Abstract: Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored. We stu
Big new release of my LLM CLI tool and Python library for talking to hundreds of different LLMs - reasoning traces, OpenAI Responses support, server-side tools, smarter logging and a whole lot more ht
arXiv:2607.25993v1 Announce Type: new Abstract: Ultra-high-resolution (UHR) remote-sensing (RS) imagery provides fine-grained Earth-observation evidence over city-scale scenes, but poses a fundamental
MCP tool design involves deciding the granularity of tools—whether they map to individual API calls or complete workflows—which directly impacts how many tools agents need and their effectiveness. Eff
arXiv:2607.03423v1 Announce Type: cross Abstract: Modern AI agent implementations such as frontier coding agents chain multiple tools at runtime that create a security surface that per-tool guardrails
arXiv:2605.11706v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to complete complex tasks by selecting and coordinating external tools across multiple steps. This re
I just released LLM 0.32a0, an alpha release of my LLM Python library and CLI tool for accessing LLMs, with some consequential changes that I've been working towards for quite a while. Previous versio
arXiv:2604.20148v1 Announce Type: cross Abstract: Can small language models achieve strong tool-use performance without complex adaptation mechanisms? This paper investigates this question through Met
arXiv:2604.19945v1 Announce Type: new Abstract: In this paper, we investigate the problem of how to effectively master tool-use to solve complex visual reasoning tasks for Multimodal Large Language Mo
Sebastian Raschka (rasbt) used Randal Olson's Tufte Test tool, developed by Goodeye Labs, to improve the visual quality of a machine learning benchmark plot. The Tufte Test encodes seven of Tufte'...
arXiv:2609.39450v1 Announce Type: cross Abstract: LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. Howev
arXiv:2609.35479v1 Announce Type: new Abstract: The ability to design a tool for a task marks a level of intelligence beyond merely understanding, selecting, or using one. Existing methods for robotic