ADP-MA: An Interactive System for Autonomous Data Processing using Meta-Agents

Udayan Khurana

IJCAI 20260 citations

ADP-MA: An Interactive System for Autonomous Data Processing using Meta-Agents

Abstract

We demonstrate ADP-MA (Autonomous Data Processing using Meta-Agents), a system that autonomously solves a complex and diverse set of data processing tasks. Three domain-agnostic meta-agents coordinate task-specific ground agents through a multi-stage pipeline: data understanding, planning, critique, expansion, execution, and finalization. Errors are caught early via progressive sampling on small data subsets before running on full data. The system supports three execution strategies, twelve domain knowledge packs, and confidence-based early stopping. An interactive web interface lets users watch pipelines being built in real time, replay completed runs at any stage, and compare results across cases. On four benchmarks, ADP-MA reaches 90.6% on DSEval, 44.8% on KramaBench, 50.0% on DA-Code, and 70.0% on AgentBench, outperforming published single-agent baselines.

AI: Agent-based and Multi-agent SystemsAI: Humans and AI

BibTeX

@inproceedings{ijcai2026_adpmaaninteracti,
  title = {ADP-MA: An Interactive System for Autonomous Data Processing using Meta-Agents},
  author = {Udayan Khurana},
  booktitle = {IJCAI 2026},
  year = {2026}
}