Pneuma-Seeker: Relational Reification of Information Needs for Agentic Data Discovery and Preparation
cs.DB
Submitted: 2026-03-11
Updated: 2026-11-01
Code: https://github.com/TheDataStation/pneuma-seeker
Terminology
Sources
- Text2SQL is Not Enough: Unifying AI and Databases with TAG
- RADAR: Benchmarking Language Models on Imperfect Tabular Data
- KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
- Octopus: Agentic Multi-Table Discovery over Tabular Data Lakes
- L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit
- MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark
- ReAct: Synergizing Reasoning and Acting in Language Models
- A Survey of Large Language Model Agents for Question Answering
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