2 papers
cs.LG2026
Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction
Xinyi Hong, Pinjun Dong, Xinyang Yu +1
Large language model (LLM) agents increasingly rely on invoking external tools to complete real-world tasks. Tool retrieval, which selects a small task-relevant subset from a libra…
stat.ME2025
Statistical ranking with dynamic covariates
Pinjun Dong, Ruijian Han, Binyan Jiang +1
We introduce a general covariate-assisted statistical ranking model within the Plackett--Luce framework. Unlike previous studies focusing on individual effects with fixed covariate…