Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Do Tabular Foundation Models Still Need Feature Engineering?
Yifan WU, Pinjun Dong, Jiran Tao +1
Feature engineering has long been a cornerstone of tabular machine learning. Tabular foundation models (TFMs) are pretrained on a wide range of tabular datasets and applied via in-…
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…