{"type": "article", "title": "Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/beyond-outcome-rewards-step-level-self-distilled-policy-optimization-for-deep", "original_source": "https://www.machinebrief.com/news/beyond-outcome-rewards-step-level-self-distilled-policy-opti-6vjs", "published": "2026-08-14T04:00:00+00:00", "accessed": "2026-08-14", "id": "beyond-outcome-rewards-step-level-self-distilled-policy-optimization-for-deep"}