feat: enhance CyberSecurity_OWASP observation model with scenario prompt, improve GRPO batch configuration validation, and add scenario grouping for adaptive difficulty curriculum 632c145 Humanlearning commited on 12 days ago
feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment be8eade Humanlearning commited on 12 days ago