Efficiently Linking Unstructured Data for Multi-step Reasoning
cs.DB, cs.AI
Submitted: 2026-09-16
Updated: 2026-09-16
Comments: 23 pages, 9 figures
Code: https://github.com/weaviate/weaviate
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- The Design of an LLM-powered Unstructured Analytics System
- A-MapReduce: Executing Wide Search via Agentic MapReduce
- ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction
- Retrieval-Augmented Generation for Large Language Models: A Survey
- WideSeek: Advancing Wide Research via Multi-Agent Scaling
- Table-as-Search: Formulate Long-Horizon Agentic Information Seeking as Table Completion
- DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking
- SemBench: A Benchmark for Semantic Query Processing Engines
- Multi-Turn Agentic Scientific Literature Search via Workflow Induction
- Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
- Passage Re-ranking with BERT
- Graph Retrieval-Augmented Generation: A Survey
- Abacus: A Cost-Based Optimizer for Semantic Operator Systems
- Whitening Sentence Representations for Better Semantics and Faster Retrieval
- Implementing Semantic Join Operators Efficiently
- WideSearch: Benchmarking Agentic Broad Info-Seeking
- WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
Related papers
- Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries
- Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering
- Bridging Business Intent and Data: A Benchmark for Automatic Relational Data Product Generation
- DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation
- MaDI-Bench: An End-to-End Data Integration Benchmark
- Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Mediated Reasoning