mlsanityData to 14 Oct 2026

Sophrosyne: Agentic Exploration of Relational Data Systems Needs Moderation

arXiv 2605.30862 ↗First posted 29 May 2026cs.DB cs.AIcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Text2SQL agents powered by LLMs translate natural language intent into SQL by exploring the data system through tool calls before formulating the query. However, to ensure secure and scoped access, data systems construct environments with explicit API surfaces. We study and categorize these APIs exposed today as either coarse-grained or fine-grained and posit that choosing between them presents a fundamental tradeoff between cost-efficient exploration and accurate SQL generation. Most data systems expose fine-grained APIs, but this inadvertently disadvantages agents: they over-explore, incorporating irrelevant schema elements into their query formulation and produce inaccurate results. We argue that curbing over-exploration is key to the effective use of these API surfaces, and propose Sophrosyne, a data system environment that augments API responses with directives that guide the agent's exploration process. Initial results show that directives reduce over-exploration by 4.6x and boost accuracy by up to 12.4% (approx. 4 percentage points).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 44 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

13 of 44 references.

Closest ancestors · 4

Same direction, newest first

  1. 2026Arming Data Agents with Tribal Knowledge13 Feb
  2. 2026AgentSM: Semantic Memory for Agentic Text-to-SQL22 Jan
  3. 2025Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First31 Aug
  4. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration2 Feb

Other references · 9

  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  2. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  3. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  4. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 187
  5. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  6. 2024DTS-SQL: Decomposed Text-to-SQL with Small Large Language Modelscited by 45
  7. 2025Automatic Metadata Extraction for Text-to-SQLcited by 27
  8. 2025Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End Systemcited by 23
  9. 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQLcited by 13

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL
  2. 2025QueryGym: Step-by-Step Interaction with Relational Databases
  3. 2025A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback
  4. 2026An Agentic System for Schema Aware NL2SQL Generation
  5. 2026A Cost-Aware Agentic Architecture for NL-to-SQL over Nested Enterprise Schemas, with a New Benchmark
  6. 2025RAISE: Reasoning Agent for Interactive SQL Exploration
  7. 2026A Semantic-Layer-Mediated Agent for Natural Language to SQL over Heterogeneous Enterprise Databases
  8. 2025Rethinking Query Optimization for Multi-Agent Systems [Vision]