Search: “tools”

arXiv:2509.15651v2 Announce Type: replace Abstract: Assessing the impact the training data on machine learning models is crucial for understanding the behavior of the model, enhancing the transparency

arXiv:2604.13109v1 Announce Type: cross Abstract: We present a two-stage pipeline for AI-assisted improvement of published algorithm implementations. In the first stage, a large language model with re

arXiv:2604.13456v1 Announce Type: cross Abstract: Woody Breast (WB) and Spaghetti Meat (SM) myopathies significantly impact poultry meat quality, yet current detection methods rely either on subjectiv

arXiv:2610.14956v1 Announce Type: new Abstract: The Model Context Protocol provides a shared interaction substrate for the agentic web, allowing heterogeneous services to expose capabilities through a

arXiv:2610.03894v1 Announce Type: cross Abstract: A deployed LLM agent emits tool calls, queries, and code that can be silently wrong -- by the time the error surfaces, the action has run. Frontier ch

arXiv:2610.00797v1 Announce Type: new Abstract: Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool cal

arXiv:2609.26900v1 Announce Type: cross Abstract: A language model agent acts through the tools it is given. The data it reads while working on a task can redirect what it does with those tools. A gro

arXiv:2609.22573v1 Announce Type: cross Abstract: LLM agents translate natural-language context, which may include attacker-controlled text, into privileged tool calls, so authorization must remain ef

arXiv:2609.21468v1 Announce Type: new Abstract: This paper studies agentic image restoration, in which multimodal agents coordinate specialized restoration tools to recover images affected by complex

arXiv:2609.17515v1 Announce Type: new Abstract: Pruning can reduce the deployment cost of large language models (LLMs), but its impact on context-grounded tool calling remains poorly understood. We sy

arXiv:2606.12821v2 Announce Type: replace Abstract: Environmental scientists spend disproportionate effort on data wrangling rather than analysis. New AI agents can be a helpful tool, but no benchmark

arXiv:2609.03966v1 Announce Type: new Abstract: Agent evaluations report a tool-call rate read off the serving stack. That number can be zero while the model is emitting well-formed calls: the interfa

arXiv:2609.03206v1 Announce Type: cross Abstract: Using a zoom-in tool is an important foundational part of modern visual agents, because it allows to efficiently handle tasks involving high-resolutio

arXiv:2509.23426v3 Announce Type: replace Abstract: AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because

arXiv:2607.17082v2 Announce Type: replace-cross Abstract: Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results. Current eva

arXiv:2606.18037v2 Announce Type: replace Abstract: Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous evidence sources, including search, APIs, datab

arXiv:2509.21842v2 Announce Type: replace Abstract: Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools/resources for travel itinerary generati

arXiv:2603.27742v2 Announce Type: replace Abstract: Vision-language agents that orchestrate specialized tools for image restoration (IR) have emerged as a promising method, yet most existing framework

arXiv:2603.12056v3 Announce Type: replace Abstract: Multimodal agents can now tackle complex reasoning tasks with diverse tools, yet they still suffer from inefficient tool use and inflexible orchestr

arXiv:2606.25447v1 Announce Type: cross Abstract: Tool-integrated LLM agents are often wrapped within a harness: the scaffolding that determines which tools are exposed, how they are described, and wh

arXiv:2601.23132v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in tool-driven environments such as healthcare analytics, financial systems, retrieval-

arXiv:2605.30454v1 Announce Type: cross Abstract: Tool-augmented LLM agents are vulnerable to prompt injection: a third party who controls part of the agent's context can plant instructions that the a

arXiv:2605.28994v1 Announce Type: new Abstract: AI tools to support real world decision making must be able to build simulation models that inform their recommendations and render them interpretable.

arXiv:2605.28774v1 Announce Type: new Abstract: Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning

arXiv:2605.13532v1 Announce Type: new Abstract: As generative AI (GenAI) tools become easily accessible, there is promise in using such tools to support instructors. To that end, this paper examines u

arXiv:2605.02682v1 Announce Type: new Abstract: Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, a

arXiv:2409.00557v4 Announce Type: replace-cross Abstract: Equipped with the capability to call functions, modern large language models (LLMs) can leverage external tools for addressing a range of task

arXiv:2604.20087v1 Announce Type: new Abstract: Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how

arXiv:2604.18874v1 Announce Type: new Abstract: Tool-integrated agents are deployed on the premise that external tools ground their outputs in reality. Yet this very reliance creates a critical attack

arXiv:2610.20384v1 Announce Type: new Abstract: Agents for mixed-degradation image restoration typically learn what a tool does to an image only after running it: failed calls waste computation and ha

arXiv:2606.22936v2 Announce Type: replace Abstract: Tool-using LLM agents make early choices about what to search for, which evidence to trust, and what to do next. A wrong early choice can steer ever

arXiv:2610.08018v1 Announce Type: new Abstract: Reliable tool use requires more than triggering a mechanism or matching a query to an API description. Before selecting a specific tool, an agent must f

arXiv:2610.03448v1 Announce Type: cross Abstract: LLM agents increasingly screen tool outputs with small prompt-injection detectors, and teams choose among detectors by their scores on public benchmar

arXiv:2610.02001v1 Announce Type: new Abstract: Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows t

arXiv:2609.24997v1 Announce Type: new Abstract: Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to sat

arXiv:2609.18128v1 Announce Type: new Abstract: Large language model (LLM) agents augmented by tools can automate complex, multi-step tasks, such as web navigation, code generation, and workflow orche

arXiv:2609.15995v1 Announce Type: new Abstract: Emerging AI regulation mandates bias audits of high-risk systems, and audit scores are beginning to be used to rank models. Both uses assume different a

arXiv:2609.13548v1 Announce Type: new Abstract: Web agents can utilize reusable tools to reduce the cost and latency of low-level browser interaction, but automatically discovered tool collections can

arXiv:2604.17125v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) widens the prompt injection attack surface of large language model applications to tool descriptions, paramet

arXiv:2608.29128v1 Announce Type: new Abstract: Tool-using agents are commonly evaluated by a single bit: whether an end-to-end workflow completed. This metric fails to distinguish failures that matte

arXiv:2608.27439v1 Announce Type: cross Abstract: LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state ch

arXiv:2608.26563v1 Announce Type: new Abstract: Agentic (tool-using) language models are mainly trained on tool-call traces and agent trajectories during post-training. These data provide direct behav

arXiv:2608.23911v1 Announce Type: new Abstract: Supervised fine-tuning on teacher-generated trajectories is the standard first stage for distilling tool-calling capabilities into deployable models. Po

arXiv:2608.18351v1 Announce Type: cross Abstract: Tool-using large language-model agents can complete a task while exercising authority that the user did not grant or the task does not need, causing e

arXiv:2608.17671v1 Announce Type: cross Abstract: Automated security patch backporting is critical for mitigating N-day vulnerabilities. Recent tools report success rates above 80% on their respective

arXiv:2608.16891v1 Announce Type: new Abstract: Agentic AI systems request tool actions that can modify files, send messages, launch jobs, or change workflow state. This shifts the safety problem from