TurnOPD: Efficient Policy Distillation for Long-Horizon Agents
Tencent-Hunyuan · hf · 2026-07-08
Tencent Hunyuan proposed TurnOPD to address the inefficiencies of full-horizon rollout and the shallow concentration of token distributions in long-horizon agent training. It introduces an episode-level budget strategy for efficient on-policy distillation.
More from coding & agent
- Devin adds e2b sandboxes for remote agent execution — badphilosopher · 2026-07-22
- Hermes Agent Refactoring Proposal: Decoupling via Event Bus and Monorepo Slicing — Promptmethus · 2026-07-22
- ty now reads Pydantic config keywords and field metadata — charliermarsh · 2026-07-22
- Pensar Launches AI Security Agent to Autonomously Discover and Patch 0-Days — andriy_mulyar · 2026-07-22
- ty adds first-class Pydantic support, including strict and lax field handling — charliermarsh · 2026-07-22
- Google launches Gemini 3.5 Flash Cyber for CodeMender, with limited access for governments — GoogleAI · 2026-07-22