The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little co…

This paper presents Mana, a sim-to-real framework for dexterous articulated tool manipulation.

The paper introduces AsyncTool, a new benchmark designed to evaluate LLM agents' ability to handle multiple, concurrent tasks with delayed tool feedback, demonstrating that asynchronous coordination i…

The paper introduces E-Bench, a synthetic benchmark for evaluating multi-step tool use in Large Language Models across three product domains.

The paper introduces ToolSciVer, a framework for multimodal scientific claim verification using three type-aware visual tools and GRPO for training.

This paper proposes a data-driven framework for contact force estimation in Deformable Tool Manipulation using a compact LSTM and few-shot adaptation strategy.

The paper identifies Mid-Session Tool Injection (MSTI) as a novel threat in the WebMCP protocol, demonstrating that attackers can manipulate the visible or perceived set of tools available to AI agent…

The paper identifies 'memory-induced tool-drift,' a systematic vulnerability where personality biases stored in an LLM agent's memory silently corrupt tool-calling decisions, even when those biases ar…

The paper introduces Policy-First Tooling, a model-agnostic permission layer that significantly enhances the safety and reliability of tool-orchestrated AI workflows by enforcing explicit constraints…

This study investigates how micro-changes in guitar pick plucking trajectory impact acoustic guitar sound using a robotic plucker and six different pick materials.

Tool Forge is a validation-carrying toolchain that converts natural language capability intent into governed, sandbox-verified tool artifacts, significantly improving agent efficiency and reliability.

This ethnographic study examines how professional music producers use AI and automated tools, finding that the tension between the need for speed and maintaining creative control is a key area for fut…

This study analyzes global usage patterns of generative AI among early adopters, finding that usage varies significantly by country income, with schooling being the primary use in low-income countries…

This paper proves a coarse tree decomposition of graphs with bounded adhesion sets and separators.

The paper proposes an architectural proxy (MCP) to enforce robust, reliable tool access control for LLM agents, demonstrating that this structural enforcement is necessary because prompt-based restric…

The paper introduces TRUSTDESC, a novel framework that prevents tool poisoning attacks in LLM applications by automatically generating highly accurate and trusted tool descriptions directly from the t…