The paper introduces a layered vulnerability framework and attack taxonomy for LLM-driven data agents and demonstrates attacks on four open-source and two production systems.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
PrepBench is a benchmark showing that state-of-the-art LLMs still struggle with natural-language-driven data preparation involving disambiguation, code generation, and workflow translation.
DataMaster deploys an AI agent to autonomously engineer data via tree search over external sources, shared candidate pools, and memory of past outcomes, yielding 32% higher medal rates on MLE-Bench Lite and a small GPQA gain over the base instruct model.
AgenticDataBench is a new benchmark covering realistic data science tasks across 15 domains using extracted skills and LLM-generated workflows to evaluate data agents at fine granularity.
DataCOPE uses verifier-guided contrastive distillation from agent trajectories to discover skills, yielding average gains of 9.71% on report-style and 32.30% on reasoning-style data analysis tasks across four model settings.
Pneuma-Seeker is an agentic system that reifies underspecified information needs on relational data into explicit relational specifications for iterative refinement, targeted discovery, and provenance-aware execution.
citing papers explorer
-
Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems
The paper introduces a layered vulnerability framework and attack taxonomy for LLM-driven data agents and demonstrates attacks on four open-source and two production systems.
-
PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?
PrepBench is a benchmark showing that state-of-the-art LLMs still struggle with natural-language-driven data preparation involving disambiguation, code generation, and workflow translation.
-
DataMaster: Data-Centric Autonomous AI Research
DataMaster deploys an AI agent to autonomously engineer data via tree search over external sources, shared candidate pools, and memory of past outcomes, yielding 32% higher medal rates on MLE-Bench Lite and a small GPQA gain over the base instruct model.
-
AgenticDataBench: A Comprehensive Benchmark for Data Agents
AgenticDataBench is a new benchmark covering realistic data science tasks across 15 domains using extracted skills and LLM-generated workflows to evaluate data agents at fine granularity.
-
Unsupervised Skill Discovery for Agentic Data Analysis
DataCOPE uses verifier-guided contrastive distillation from agent trajectories to discover skills, yielding average gains of 9.71% on report-style and 32.30% on reasoning-style data analysis tasks across four model settings.
-
Demonstration of Pneuma-Seeker: Agentic System for Reifying and Fulfilling Information Needs on Tabular Data
Pneuma-Seeker is an agentic system that reifies underspecified information needs on relational data into explicit relational specifications for iterative refinement, targeted discovery, and provenance-aware execution.
- An Agentic Approach to Metadata Reasoning