tool-retrieval

Tag

Cards List
#tool-retrieval

The Menu Is an Execution Prior: State-Path Tool Menus for Online Agents

arXiv cs.AI · 2026-09-11 Cached

This paper introduces the tool menu as an execution prior and proposes the State-Path Tool Menu framework to improve online agent success rates by learning execution routes for tool retrieval in multi-step tasks.

0 favorites 0 likes
#tool-retrieval

TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs

Hugging Face Daily Papers · 2026-06-22 Cached

TRACE introduces a two-stage curriculum to preserve parametric tool knowledge in enterprise LLMs while enabling fast single-beam greedy decoding, achieving improved accuracy and recall over baselines.

0 favorites 0 likes
#tool-retrieval

ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs

arXiv cs.AI · 2026-06-12 Cached

ToolSense is an open-source diagnostic framework that generates three benchmarks (realistic retrieval, MCQ probing, QA probing) to audit LLMs' parametric tool knowledge, revealing a knowledge-retrieval dissociation where strong retrieval performance can coexist with poor factual understanding.

0 favorites 0 likes
#tool-retrieval

Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System

arXiv cs.AI · 2026-06-04 Cached

BioManus is an MCP-native biomedical agent system that uses graph-scaffolded planning over structured biological capabilities instead of flat prompt-based tool retrieval, achieving better context efficiency and execution accuracy on biomedical benchmarks. The system introduces a BioinfoMCP Compiler to standardize heterogeneous bioinformatics tools and organizes them as a typed heterogeneous MCP graph for scalable reasoning.

0 favorites 0 likes
#tool-retrieval

CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval

arXiv cs.AI · 2026-05-29 Cached

CoHyDE introduces an iterative co-training procedure for an LLM rewriter and a dense encoder to improve tool retrieval from large API catalogs. It outperforms single-component baselines, especially on vague queries, by training both components together using InfoNCE and DPO.

0 favorites 0 likes
← Back to home

Submit Feedback