Saved in:
Bibliographic Details
Main Authors: Liu, Hao, Li, Dongyu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.19793
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917427109953536
author Liu, Hao
Li, Dongyu
author_facet Liu, Hao
Li, Dongyu
contents LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering, but ordering depends on inter-tool data dependencies that are absent from tool descriptions. As a result, semantic-only methods can produce negative Kendall-$τ$ in structured workflow domains. We introduce SkillGraph, a directed weighted execution-transition graph mined from 49,831 successful LLM agent trajectories, which encodes workflow-precedence regularities as a reusable graph foundation prior. Building on this graph foundation prior, we propose a two-stage decoupled framework: GS-Hybrid retrieval for candidate selection and a learned pairwise reranker for ordering. On ToolBench (9,965 test instances; ~16,000 tools), the method reaches Set-F1 = 0.271 and Kendall-$τ$ = 0.096; on API-Bank, Kendall-$τ$ improves from -0.433 to +0.613. Under identical Stage-1 inputs, the learned reranker also outperforms LLaMA-3.1-8B Stage-2 rerankers.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19793
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation
Liu, Hao
Li, Dongyu
Artificial Intelligence
Computation and Language
Information Retrieval
Machine Learning
LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering, but ordering depends on inter-tool data dependencies that are absent from tool descriptions. As a result, semantic-only methods can produce negative Kendall-$τ$ in structured workflow domains. We introduce SkillGraph, a directed weighted execution-transition graph mined from 49,831 successful LLM agent trajectories, which encodes workflow-precedence regularities as a reusable graph foundation prior. Building on this graph foundation prior, we propose a two-stage decoupled framework: GS-Hybrid retrieval for candidate selection and a learned pairwise reranker for ordering. On ToolBench (9,965 test instances; ~16,000 tools), the method reaches Set-F1 = 0.271 and Kendall-$τ$ = 0.096; on API-Bank, Kendall-$τ$ improves from -0.433 to +0.613. Under identical Stage-1 inputs, the learned reranker also outperforms LLaMA-3.1-8B Stage-2 rerankers.
title SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation
topic Artificial Intelligence
Computation and Language
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2604.19793