Skill UI

This tool executes a GEPA learning cycle, automating the evolution and optimization of policy prompts against a scored task corpus. Instead of relying on manual prompt iteration, it measures performance improvements, identifying the best working 'harness genome.' It is ideal for measuring sustainable improvements in task performance and supports a free, cost-estimating dry-run mode before committing to actual model calls.

This comprehensive guide outlines best practices for packaging and releasing scientific artifacts—including code, training configurations, demonstration data, and policy checkpoints—for robotics research papers. It details how to prepare materials for anonymous reviewer assessment and for durable public release, ensuring the work is fully reproducible by the academic community.

A comprehensive guideline for researchers developing robot-learning papers. It details best practices for experimental design, emphasizing statistical rigor, handling stochasticity (training seeds, initial states), bridging the sim-to-real gap, and ensuring fairness across baseline policy families (BC/RL/VLA). This resource helps ensure claims are supported by credible evidence.

A comprehensive guide on preparing and structuring evidence packages for recommender system research, especially for academic submissions. It details how to ensure that all ranking claims, off-policy estimates, and evaluation metrics are end-to-end reproducible by providing artifacts like datasets, split scripts, model checkpoints, and propensity logs in an anonymous, verifiable repository.

A comprehensive guide for structuring the Related Work section for top-tier recommender systems conferences (RecSys). It advises authors on auditing novelty by positioning their contribution against adjacent research fields (e.g., SIGIR, KDD, WSDM), addressing critical lines (like reproducibility and off-policy evaluation), and ensuring the work is technically distinct from prior or concurrent studies.