TL;DR
Experiments in a personalized apparel design scenario show that BATR enhances the accuracy of knowledge boundary detection and improves tool invocation stability compared with baseline methods, demonstrating improved controllability and reliability in the evaluated apparel-design tasks.
This work presents SCOUT (Selective Context Optimization for Universal Tooling for Universal Tooling), which reframes tool exposure as a context-selection problem, injecting only tools relevant to the current step, and reduces MCP tool-token consumption by 99%, cutting per-query inference cost at enterprise scale.
This work introduces Tool Primitives, a design that replaces rigid API schema-based invocation with natural language as the interface for tool calling, where each tool is wrapped with an LLM interface that handles schema resolution and execution internally, enabling natural inter-tool communication for nested and multi...
Trace analysis shows failures concentrate at language-mediated reasoning - entity disambiguation, cross-source grounding, rather than tool invocation mechanics, rather than tool invocation mechanics.
The Domain-Oriented Tooling Pattern is proposed: instead of generating SQL at query time, the model selects from a small set of domain-aligned tools whose parameterized queries encapsulate schema navigation, joins and business rules on the server side.
Recent advances in agentic recommender systems are shifting recommender systems from passive filtering engines to instruction-following agents that use external tools to resolve user intent. However, existing benchmarks often assume explicit user intent, simplified tool environments, or isolated function calls, leaving...
It is indicated that retrieval-stage filtering can reduce the candidate action space exposed to agents before execution, complementing downstream tool-use safeguards, and providing a conservative operating point for safety-critical deployments.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
