DSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Comments: 39 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Apache Calcite: A Foundational Framework for Optimized Query Processing Over Heterogeneous Data Sources
- Binding Language Models in Symbolic Languages
- DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
- Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
- Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
- AgentBench: Evaluating LLMs as Agents
- DBRouting: Routing End User Queries to Databases for Answerability
- GAIA: a benchmark for General AI Assistants
- CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
- CHESS: Contextual Harnessing for Efficient SQL Synthesis
- BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
- DBCopilot: Natural Language Querying over Massive Databases via Schema Routing
- LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL
- MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL
- ReAct: Synergizing Reasoning and Acting in Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems