Octopus: Agentic Multi-Table Discovery over Tabular Data Lakes
cs.DB
Submitted: 2026-01-05
Updated: 2026-10-28
Comments: Substantial redesign of Octopus as an agentic framework
Code: https://github.com/wenzhilics/octopus
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GPT-4 Technical Report
- Qwen Technical Report
- Qwen2.5-VL Technical Report
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- GPT-4o System Card
- DeepSeek-V3 Technical Report
- Automatic Metadata Extraction for Text-to-SQL
- LLaMA: Open and Efficient Foundation Language Models
Related papers
- Beyond Overlap: Hierarchical Graph Abstraction for Out-of-Core Vector Search
- EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
- Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
- Samyama: A Unified Graph-Vector Database with In-Database Optimization, Agentic Enrichment, and Hardware Acceleration
- GenTUS: Table Union Search via Constrained Generation of Semantic Table Identifiers
- Common-Neighbor-Count-Based Representative Possible World Finding on Uncertain Graphs