Skip to content

Selected figures

Figures

Figures from the lab's published papers, grouped by article. Swipe or use the arrows; click any figure to enlarge.

Benchmarking Agentic Tool Use and Reasoning in Repository-Level Code Comprehension

Bert T, Miljkovic N. Aura Lab Technical Report (2026). DOI

  • Figure 1: Architectural diagram of the multi-agent code comprehension and verification pipeline.

Aura-Bench: An Open Evaluation Suite for Multi-Step AI Agent Tool Execution

Bert T, Miller G, Ortega-Marquez J, Miljkovic N. Open Source Software & Datasets (2026). DOI

  • Figure 3: Aura-Bench comparative execution success rates across autonomous and verified agent configurations.

Structured Retrieval and Factuality Verification for Scientific Domain Large Language Models

Bert T et al. Aura Lab Preprints (2025). DOI

  • Figure 2: Structured retrieval architecture and factuality self-check pipeline for scientific domain datasets.