Tag: MLE-Bench

Showing 1-2 of 2

Apr 21, 20268 min readAgent PlaybookIntermediate240 min build

Minimal Compute‑Grounded Reasoning Agent: Deterministic Scene‑Graph and Entropy‑Guided Routing

Prototype a Spatial Atlas CGR agent: deterministic scene‑graph computations (distances, safety checks) feed an LLM, reducing spatial hallucination and enabling entropy‑guided routing.

spatial-ai agents compute-grounded-reasoning scene-graph benchmarks

+3 more

TutorialsUnited Kingdom

Open

Mar 18, 20269 min readAgent PlaybookIntermediate120 min build

Run AIBuildAI to automate model builds and generate reproducible evaluation reports

Practical walkthrough to clone and run AIBuildAI (ranked #1 on OpenAI MLE‑Bench). In 20–120 minutes run a demo build, generate an evaluation report, and reproduce the result.

AIBuildAI AI agents AutoML MLE-Bench GitHub

+3 more

tutorial reproducibility model-evaluation