Sophrosyne: Agentic Exploration of Relational Data Systems Needs Moderation

• URL: http://arxiv.org/abs/2605.30862v1
• Date: Fri, 29 May 2026 05:37:54 GMT
• Title: Sophrosyne: Agentic Exploration of Relational Data Systems Needs Moderation
• Abstract summary: We study and categorize these APIs exposed today as either coarse-grained or fine-grained.<n>Most data systems expose fine-grained APIs, but this inadvertently disadvantages agents.<n>We propose Sophrosyne, a data system environment that augments API responses with directives that guide the agent's exploration process.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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).

Related papers

• Environment-free Synthetic Data Generation for API-Calling Agents [68.95520739708304]
  Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories.<n>We propose an environment-free synthetic data generation approach that leverages LLMs as on-the-fly digital world models.<n>We evaluate our approach on the challenging AppWorld and OfficeBench benchmarks, which include both information-retrieval and state-changing tasks.
  arXiv  Detail & Related papers  (2026-07-18T17:36:44Z)
• ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL [51.98164069124653]
  ProSPy is a Profiling-driven framework for enterprise-scale Text-to-gnostic analysis.<n>ProSPy structures the reasoning process into four stages.<n>It first extracts fine-grained data evidence through automatic profiling.<n>It prunes large schemas into task-relevant contexts.
  arXiv  Detail & Related papers  (2026-06-04T08:13:05Z)
• APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL [39.76924093980244]
  APEX- verbalize is a framework that shifts the paradigm from passive translation to agentic exploration.<n>Our framework employs a hypothesis-verification loop to ground model reasoning in real data.
  arXiv  Detail & Related papers  (2026-02-11T07:50:47Z)
• Enhancing the Capabilities of Large Language Models for API calls through Knowledge Graphs [1.6691048566825868]
  KG2data is a system that integrates knowledge graphs, large language models (LLMs), ReAct agents, and tool-use technologies.<n>Using a virtual API, we evaluate API call accuracy across three metrics: name recognition failure, hallucination failure, and call correctness.<n> KG2data achieves superior performance (1.43%, 0%, 88.57%) compared to RAG2data (16%, 10%, 72.14%) and chat2data (7.14%, 8.57%, 71.43%)
  arXiv  Detail & Related papers  (2025-07-14T08:20:06Z)
• Invocable APIs derived from NL2SQL datasets for LLM Tool-Calling Evaluation [7.260113022127256]
  Large language models (LLMs) are routinely deployed as agentic systems with access to tools that interact with live environments to accomplish tasks.<n>In order to create datasets with such characteristics, we explore how existing NL2 datasets can be used to automatically create NL2API datasets.<n>We apply this pipeline to one of the largest NL2 datasets, BIRD, to create a collection of over 2500 APIs that can be served as invocable tools or REST-endpoints.
  arXiv  Detail & Related papers  (2025-06-12T20:17:52Z)
• RAISE: Reasoning Agent for Interactive SQL Exploration [47.77323087050061]
  We propose a novel framework that unifies schema linking, query generation, and iterative refinement within a single, end-to-end component.<n>Our method emulates how humans answer questions when working with unfamiliar databases.
  arXiv  Detail & Related papers  (2025-06-02T03:07:08Z)
• ToolACE: Winning the Points of LLM Function Calling [139.07157814653638]
  ToolACE is an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data.<n>We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard.
  arXiv  Detail & Related papers  (2024-09-02T03:19:56Z)
• Get my drift? Catching LLM Task Drift with Activation Deltas [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.<n>We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.<n>We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• Compositional API Recommendation for Library-Oriented Code Generation [23.355509276291198]
  We propose CAPIR, which adopts a "divide-and-conquer" strategy to recommend APIs for coarse-grained requirements. We present two challenging benchmarks, RAPID (Recommend APIs based on Documentation) and LOCG (Library-Oriented Code Generation) Experimental results on these benchmarks, demonstrate the effectiveness of CAPIR in comparison to existing baselines.
  arXiv  Detail & Related papers  (2024-02-29T18:27:27Z)
• Allies: Prompting Large Language Model with Beam Search [107.38790111856761]
  In this work, we propose a novel method called ALLIES. Given an input query, ALLIES leverages LLMs to iteratively generate new queries related to the original query. By iteratively refining and expanding the scope of the original query, ALLIES captures and utilizes hidden knowledge that may not be directly through retrieval.
  arXiv  Detail & Related papers  (2023-05-24T06:16:44Z)
• PyODDS: An End-to-end Outlier Detection System with Automated Machine Learning [55.32009000204512]
  We present PyODDS, an automated end-to-end Python system for Outlier Detection with Database Support. Specifically, we define the search space in the outlier detection pipeline, and produce a search strategy within the given search space. It also provides unified interfaces and visualizations for users with or without data science or machine learning background.
  arXiv  Detail & Related papers  (2020-03-12T03:30:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.