RelAgent is an LLM-based autonomous data scientist designed for relational learning. It operates in two phases: first, the LLM agent constructs SQL feature programs and selects a predictive model using database, validation, and evaluation tools; second, the resulting program is executed without further LLM calls. The final predictor combines SQL queries and a classical model, providing fast, deterministic, and interpretable predictions that rely solely on human-readable query-defined features.
Prior-data fitted networks (PFNs) show that pretraining on large populations of synthetic tasks can enable generalization to unseen datasets with little or no downstream fine-tuning. This paradigm is...
arXiv:2606. 03040v1 Announce Type: new Abstract: Relational databases underpin modern enterprise, scientific, and healthcare systems, yet predictive machine learning on such data remains challenging due to their multi-table, heterogeneous, and temporal structure.
The paper investigates whether prior‑data‑fitted networks (PFNs) can be extended to graph‑based relational models. The authors pretrain a message‑passing foundation model, Griffin, on large synthetic relational databases and evaluate its frozen encoder on 16 real‑world relational classification tasks. A curriculum that starts with schema‑guided synthetic data and then uses schema‑agnostic data yields the best in‑context performance, outperforming real‑data‑only pretraining and other mixtures.
MetaRTL is a two-stage framework for relational table learning that first generates lightweight pre-trained table embeddings and then applies non‑parametric message passing to extract meta‑path features. These features are aggregated using an attention module called MetaAttn, shifting computation from deep GNN stacks to efficient meta‑path aggregation. Experiments on 10 real‑world datasets across 24 tasks show that MetaRTL achieves strong performance while reducing computational cost.
arXiv:2608. 16319v1 Announce Type: new Abstract: This first release of Prior Labs in relational learning shows our continued commitment to open science.
The paper introduces FlockMTL, an extension for database management systems that deeply integrates large language models and retrieval‑augmented generation into DuckDB. It provides model‑driven scalar and aggregate functions, cost‑based optimizations like batching and caching, and new SQL DDL abstractions (PROMPT and MODEL) to treat LLMs as first‑class schema objects. These features aim to simplify the development of knowledge‑intensive analytical applications by reducing the effort required to orchestrate heterogeneous data systems and manage LLM context.
Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientific and industrial domains. However, adapting existing models to unseen datasets...
arXiv:2602. 09572v3 Announce Type: replace-cross Abstract: The purpose of predictive modeling on relational data is to predict future or missing values in a relational database, for example, future purchases of a user, risk of readmission of the patient, or the likelihood that a financial transaction is fraudulent.
arXiv:2605. 30407v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated strong performance on general tasks, while often struggling to adapt to specialized domains without high-quality domain-specific data.
arXiv:2610.17867v2 Announce Type: cross Abstract: Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientific and industrial domains. Ho...
arXiv:2609.01292v1 Announce Type: cross Abstract: Relational Deep Learning (RDL) has become a powerful paradigm for learning from multi-tabular data. However, manually defining RDL prediction tasks i...
The paper investigates whether large language models (LLMs) can leverage frozen relational‑transformer embeddings by injecting them as soft tokens. Using a learned MLP projection and LoRA adaptation, the authors fine‑tune Qwen3.5‑4B on chain‑of‑thought reasoning traces and group‑based reinforcement learning, then evaluate on ten binary classification tasks across six RelBench databases. The hybrid approach consistently underperforms the standalone relational transformer, showing sensitivity to serialization format, token budget, and RL stability, leading the authors to conclude that stronger alignment objectives and schema‑aware design are needed for reliable relational prediction.