Spaces:
Sleeping
Sleeping
feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment
be8eade | { | |
| "scenario_author": { | |
| "provider": "huggingface", | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "thinking_mode": "thinking", | |
| "reasoning_effort": "high", | |
| "temperature": 1.0, | |
| "top_p": 1.0, | |
| "max_context_tokens": 131072 | |
| }, | |
| "curriculum": { | |
| "difficulty_bucket_count": 4, | |
| "difficulty_labels": ["D0", "D1", "D2", "D3"], | |
| "train_scenarios_per_bucket": 25, | |
| "validation_scenarios_per_bucket": 10, | |
| "heldout_eval_scenarios_per_bucket": 10, | |
| "target_cache_hit_rate": 0.95, | |
| "target_reset_latency_ms": 200, | |
| "scenario_refresh_rate_per_epoch": 0.05, | |
| "difficulty_calibration_strategy": "baseline_agent_pass_rate", | |
| "pass_rate_thresholds": { | |
| "D0": [0.8, 1.0], | |
| "D1": [0.6, 0.8], | |
| "D2": [0.4, 0.6], | |
| "D3": [0.2, 0.4] | |
| } | |
| }, | |
| "runtime": { | |
| "cache_mode": "fallback", | |
| "cache_dir": "scenario_cache", | |
| "generator_version": "scenario_generator_v1", | |
| "verifier_version": "verifier_v1" | |
| } | |
| } | |