{ "task": "calendar_tool_calling", "timezone": "Asia/Seoul", "samples": 400, "models": [ { "model": "Qwen3-4B Base", "valid_tool_call": 1.0, "policy_compliance": 0.8, "task_success": 0.2, "average_tool_calls": 0.8 }, { "model": "Calendar Agent SFT", "valid_tool_call": 1.0, "policy_compliance": 0.8925, "task_success": 0.89, "average_tool_calls": 2.5525 }, { "model": "Calendar Agent RLVR", "valid_tool_call": 1.0, "policy_compliance": 0.9925, "task_success": 0.99, "average_tool_calls": 2.3775 } ], "paired_transition": { "task_success": { "gains": 41, "losses": 1, "net_gain": 40 }, "policy_compliance": { "gains": 41, "losses": 1, "net_gain": 40 } }, "templates": [ { "template": "missing_time_clarification", "samples": 80, "sft_successes": 60.0, "rlvr_successes": 80.0 }, { "template": "delete_confirmation", "samples": 80, "sft_successes": 59.0, "rlvr_successes": 80.0 }, { "template": "conflict_then_create", "samples": 80, "sft_successes": 77.0, "rlvr_successes": 76.0 }, { "template": "confirmed_delete", "samples": 80, "sft_successes": 80.0, "rlvr_successes": 80.0 }, { "template": "multi_attendee_create", "samples": 80, "sft_successes": 80.0, "rlvr_successes": 80.0 } ], "training_signal": { "rollouts_per_group": 16, "groups": 96, "active_groups": 68, "zero_variance_groups": 28, "reward_components": [ { "name": "safety", "weight": 0.25 }, { "name": "policy_progress", "weight": 0.35 }, { "name": "semantic_final_success", "weight": 0.4 } ] } }