Knowledge catalogue
arXiv:2609.14758v1 Announce Type: cross Abstract: Tool-augmented language models are evaluated on whether they reach the right answer, not on whether they report honestly when a tool fails to supply o
arXiv:2609.14157v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed with external tools that extend what they can do beyond their own knowledge. Tools help on tasks
Is Bash All You Need? Interesting paper from Microsoft. If you are deciding which tools to give an enterprise agent, you might want to check this out. (bookmark it) They compared five tool interfaces
arXiv:2609.05587v1 Announce Type: new Abstract: Existing evaluations of tool-using agents primarily measure whether an agent can successfully complete diverse tasks with tools. These evaluations gener
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:2604.08281v1 Announce Type: new Abstract: Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of
arXiv:2604.19749v1 Announce Type: new Abstract: Equipping LLMs with external tools effectively addresses internal reasoning limitations. However, it introduces a critical yet under-explored phenomenon
Auto-generated index of all tools mentioned across the wiki.
arXiv:2510.07248v3 Announce Type: replace Abstract: Small language models (SLMs) enable scalable tool-augmented multi-agent systems where multiple SLMs handle subtasks orchestrated by a powerful coord
arXiv:2608.21544v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can depend on tool calls and external observations ra
arXiv:2608.03327v1 Announce Type: new Abstract: Hybrid computer-use agents can act through screenshots or call text tools. We find that having a tool available does not settle which way the effect goe
arXiv:2607.25718v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on invoking external tools to complete real-world tasks. Tool retrieval, which selects a small tas
Meta announced Muse Spark today, their first model release since Llama 4 almost exactly a year ago. It's hosted, not open weights, and the API is currently 'a private API preview to select users', but
arXiv:2610.08097v1 Announce Type: cross Abstract: Mathematical problem solving often requires deterministic computational steps that agents delegate to tools and implicitly trust. Yet tools can fail s
One cool thing deepagents now supports: dynamically loading tools when is a skill is loaded Some skills require specific tools that you may not always want to have available. This now allows you to pa
Track usage and costs across your users, agents and tools. We're also shipping better access controls for your tools & agents: - Set spend limits on agents - Set spend limits for users - Control what
arXiv:2604.12743v1 Announce Type: new Abstract: While recent research has explored AI tools' ability to classify the quality of mathematical tasks (arXiv:2603.03512), little is known about their capac
arXiv:2610.09624v1 Announce Type: cross Abstract: Tool calling, invoking external tools on demand, is central to agentic LLMs, yet the mechanism that decides whether a model calls a tool or responds d
arXiv:2609.30906v1 Announce Type: new Abstract: Large language models (LLMs) excel at natural language processing but struggle to interact with external environments. Tool learning provides a promisin
arXiv:2609.30698v1 Announce Type: new Abstract: Real-world multimodal misinformation often involves mixed forgery sources, requiring sample-specific detection strategies. Existing tool-augmented metho
arXiv:2608.04719v1 Announce Type: new Abstract: Agent evaluations tell us that a model picked the wrong tool, but rarely why. We introduce canary tools: diagnostic probe tools planted in an agent's Mo
arXiv:2608.09682v1 Announce Type: new Abstract: Tool-augmented vision-language models increasingly 'think with images': they call crop, zoom, or code tools and reason over the returned pixels. However
arXiv:2608.08907v1 Announce Type: cross Abstract: Thinking with images allows a multimodal model to compensate for limited perception by invoking visual tools through code. Yet the prevailing SFT-then
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:2608.00218v1 Announce Type: new Abstract: Agentic LLMs exhibit three consequential tool-use failures: invalid arguments (validity), unnecessary calls (over-calling), and omitted calls when tools
I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider t
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:2605.24660v1 Announce Type: cross Abstract: Before an LLM agent can use a tool, a retrieval system must decide which candidate tools to show to the agent. How long should that shortlist be? Show
arXiv:2510.20036v2 Announce Type: replace Abstract: Large language model (LLM) agents rely on external tools to solve complex tasks, but real-world toolsets often contain redundant tools with overlapp
arXiv:2605.09252v1 Announce Type: new Abstract: Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latenc
arXiv:2604.21816v1 Announce Type: new Abstract: The Model Context Protocol (MCP) has become a common interface for connecting large language model (LLM) agents to external tools, but its reliance on s
arXiv:2605.00136v1 Announce Type: new Abstract: Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we
☁️ Salesforce tools now in Fleet One of the most requested features we've gotten, and it's now a first-class supported tool in Fleet! Just sign in with your Salesforce account, and start using it imme
arXiv:2605.19852v1 Announce Type: new Abstract: Tool-augmented reasoning has emerged as a promising direction for enhancing the reasoning capabilities of multimodal large language models (MLLMs). Howe
Opened a llama.cpp discussion about whether custom GBNF grammars can compose with tool calls in llama-server. Right now tools work alone, grammar works alone, but tools+grammar doesn't. If you use lla
arXiv:2606.02483v1 Announce Type: cross Abstract: Tool-augmented language agents speculatively issue likely future tool calls to hide latency, but those calls leak inferred user intent to external ser
arXiv:2512.04069v2 Announce Type: replace Abstract: Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required f
arXiv:2609.37153v1 Announce Type: new Abstract: Tool-augmented data agents rely on tool outputs for analytical decisions. Yet successful execution can return plausible but incorrect evidence, requirin
We talked about Claude Code, Claude Tag, Fable, coding agent security, evals, tool design, and how Anthropic use these tools themselves Claude Tag (Claude Code via Slack) is already landing 65% of the
arXiv:2509.23292v4 Announce Type: replace Abstract: Tool-integrated reasoning (TIR) has become a key approach for improving large reasoning models (LRMs) on complex problems. Prior work has mainly stu
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,
Finally, a people-search tool that actually works. Most people-search tools sell you a frozen list. @CLODOAI searches the live web, reads the signals, and tells you why this specific person, right now
Better Models: Worse Tools Armin reports on a weird problem he ran into while hacking on Pi: The short version is that newer Claude models sometimes call Pi’s edit tool with extra, invented fields in
Some people here say MiMo-V2.6 is bad with tools and are going back to GLM-5.3-Flash. I spent today running MiMo-V2.6-Flash-RL as the backend for an agent harness, on 2× DGX Spark with vLLM, using the
arXiv:2511.09572v2 Announce Type: replace Abstract: For agentic systems to use external tools to solve complex, long-horizon tasks, we need a large set of diverse and controllable tool-use environment
arXiv:2605.26637v1 Announce Type: new Abstract: Most existing embodied intelligence methods formulate perception, reasoning, planning, and control within a unified parameterized policy. Yet these capa
How is AI really affecting your job? @Cohere_Labs released the Agentic Task Ecosystem, a new dataset of 690K+ tools built for AI agents. Under a test of whether a tool could independently complete an
arXiv:2606.12451v2 Announce Type: replace-cross Abstract: Large language models deployed as agents over large tool catalogs face a critical tool-retrieval bottleneck. As embedding-based retrieval appr
EVA-Bench Data 2.0 is an expanded benchmark dataset containing tools and scenarios across 3 domains, featuring 121 tools and 213 test scenarios for evaluating AI agent performance. This dataset enable
arXiv:2609.39378v1 Announce Type: new Abstract: Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolving
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
arXiv:2608.17007v1 Announce Type: new Abstract: Agent Skills can specify procedural and resource obligations for tool use, and language models instantiate them as concrete programs. However, when mode
arXiv:2607.03953v1 Announce Type: cross Abstract: This study independently replicates and extends the Natural Language Tools (NLT) framework of Johnson et al.~(2025), which questions the use of struct
arXiv:2505.21569v3 Announce Type: replace-cross Abstract: Although LLM-based agents are proven to master tool orchestration in scientific fields, particularly chemistry, their single-task performance
arXiv:2604.13519v1 Announce Type: new Abstract: Tool calling has greatly expanded the practical utility of large language models (LLMs) by enabling them to interact with external applications. As LLM
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
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: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