yousha806/graph-webagents

How yousha806/graph-webagents works

Graph-WebAgents is a Multimodal Mind2Web data-preparation and web-agent research repository. Its documented workflow is to obtain dataset splits, optionally enrich them with accessibility-tree representations, load batches, run baseline inference, and evaluate predictions. The graph preserves the major model families and evaluation tools. Some inference scripts are templates or baselines; connections between unsampled modules are included only where documented, and are otherwise omitted.

Main entry points: mind2web_dataloader.py Mind2Web DataLoader · batch_inference.py Batch Inference Template · precompute_axtree.py AXTree Precompute · vlm_inference.py VLM Baseline

Components 19

Dataset Preparation

Local Splits
Split Downloader download_mind2web.py
AXTree Precompute precompute_axtree.py
Enriched Splits

Dataset Access

Mind2Web DataLoader mind2web_dataloader.py

Agent Baselines

GAT Pretraining baselines/models/GAT_Pretrain.py
Multimodal GNN baselines/models/multimodal_GNN.py
Cross-Attention GNN baselines/models/multimodal_GNN_Cross.py
Graph LoRA Model baselines/models/mmml_metrics_merged.py
Multimodal Instruct baselines/models/multimodal_instruct.py
Qwen Instruct baselines/models/multimodal_qwen_instruct.py
Text-Only Baseline baselines/models/text_only.py
VLM Baseline baselines/models/vlm_inference.py

Inference Evaluation

Batch Inference Template inference/batch_inference.py
Next-Action Evaluator eval_next_action.py
Prediction Metrics inference/vlm_inference_script.py

Other components

Researcher
Mind2Web Dataset
Headless Chromium

Connections 27

Researcher → Split Downloader: selects splits README.md
Split Downloader → Mind2Web Dataset: downloads download_mind2web.py
Split Downloader → Local Splits: saves splits download_mind2web.py
Researcher → AXTree Precompute: requests enrichment README.md
AXTree Precompute → Mind2Web Dataset: loads split precompute_axtree.py
AXTree Precompute → Headless Chromium: renders HTML precompute_axtree.py
AXTree Precompute → Enriched Splits: saves enriched data precompute_axtree.py
Researcher → Mind2Web DataLoader: requests batches README.md
Local Splits → Mind2Web DataLoader: loads local split mind2web_dataloader.py
Mind2Web Dataset → Mind2Web DataLoader: loads directly README.md
Mind2Web DataLoader → GAT Pretraining: provides dataset inputs
Mind2Web DataLoader → Multimodal GNN: provides dataset inputs
Mind2Web DataLoader → Cross-Attention GNN: provides dataset inputs
Mind2Web DataLoader → Graph LoRA Model: provides dataset inputs
Mind2Web DataLoader → Multimodal Instruct: provides dataset inputs
Mind2Web DataLoader → Qwen Instruct: provides dataset inputs
Mind2Web DataLoader → Text-Only Baseline: provides dataset inputs
Mind2Web DataLoader → VLM Baseline: provides dataset inputs
Researcher → Batch Inference Template: runs inference inference/batch_inference.py
Batch Inference Template → VLM Baseline: dispatches baseline
Batch Inference Template → Multimodal GNN: dispatches baseline
Batch Inference Template → Cross-Attention GNN: dispatches baseline
Batch Inference Template → Text-Only Baseline: dispatches baseline
VLM Baseline → Next-Action Evaluator: emits predictions
VLM Baseline → Prediction Metrics: emits predictions
Researcher → Next-Action Evaluator: evaluates predictions eval_next_action.py
Researcher → Prediction Metrics: evaluates predictions inference/vlm_inference_script.py

Drawn by GitDiagram on November 11, 2026 from the repository's file tree, README and source files. Read as Markdown ·