🪐 EDM-ARS · v1.0 Pilot
A multi-agent LLM pipeline that turns a dataset and a research prompt into a complete, reviewer-ready academic paper.
Overview
Inspired by FARS, EDM-ARS is a domain-specific multi-agent LLM pipeline that automates the complete workflow of prediction-focused educational data mining research. Given the HSLS:09 dataset and a research prompt, it formulates a research question, engineers features, trains and compares multiple ML models, runs SHAP explainability and subgroup fairness analysis, retrieves real citations via the Semantic Scholar API, and produces a complete ACM sigconf-formatted LaTeX paper — with a built-in Critic agent that enforces methodological rigor through automated peer review and targeted revision loops.
Built around the HSLS:09 longitudinal dataset with a hand-curated 95-variable Tier 1 registry encoding substantive educational meaning — not just column names.
The Writer fills prose into a fixed ACM sigconf LaTeX skeleton with %%PLACEHOLDER%% markers — never generating boilerplate from scratch, ensuring structurally correct output every time.
After analysis, the Critic reviews all prior agents' outputs and can route targeted revisions back to any stage — up to 2 cycles — before writing begins.
Pipeline state is serialized to checkpoint.json after every stage. Interrupted runs resume from the last completed stage — no work is lost.
Architecture
subgroup_labels & column_mapping for fairness analysisRevision loop — on REVISE, targeted instructions are routed back to ProblemFormulator, DataEngineer, or Analyst selectively. Up to 2 cycles before the Writer is unblocked regardless.
Features
5 Specialized Agents
Coordinated by a state-machine orchestrator. Each agent has its own system prompt, temperature, and model tier (Opus for Critic, Sonnet for all others).
End-to-End Automation
From a raw CSV and a research prompt to a compiled ACM LaTeX paper — with real citations, methodology validation, and SHAP explainability figures.
Self-Healing Pipeline
Contract validation at every stage boundary. Auto-patching for classifiable errors (SHAP failure, dtype mismatch, missing column) before falling back to LLM repair.
Live Academic Citations
The ProblemFormulator queries the Semantic Scholar API with exponential-backoff retry logic to retrieve and validate real, current citations.
6-Model Battery
Logistic Regression, Random Forest, XGBoost, ElasticNet, MLP, and a Stacking Ensemble are trained, compared, and reported with SHAP explainability where applicable.
Docker Sandboxing
LLM-generated analysis code executes inside a Docker sandbox (network-disabled). Gracefully falls back to subprocess when Docker is unavailable.
Pilot Run Results
Numbers from the first end-to-end pipeline run, producing a complete ACM sigconf paper on HSLS:09 college-enrollment prediction.
Built With
Scope & Roadmap
The current release targets prediction tasks on HSLS:09 only. Future task modules will expand EDM-ARS into a full research automation platform for educational data science.
%%PLACEHOLDER%% markers