Understand this story
On October 19, 2026, Dongxi recommended reading the preprint paper TreeOPSD: Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning. According to the original post, this is a critic-free reinforcement learning method for long-horizon LLM agents that propagates terminal rewards back along the rollout tree and uses forward KL to align the current policy with the target at each round. The original post claims that on Deep Research, this method raises the average accuracy of Qwen3-30B-A3B-Thinking-2507 from 16.23 with GRPO to 21.20. Currently, this recommendation still relies on the original post as its sole source, with no subsequent independent reporting.
AI-generated from public reports
Latest development · Report
Dongxi recommends the TreeOPSD long-horizon agent reinforcement learning paperDevelopments
1 confirmed developments
- Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 19
Ma Dongxi NLP
Dongxi recommends the TreeOPSD long-horizon agent reinforcement learning paper
Dongxi recommends reading the preprint TreeOPSD: a critic-free reinforcement learning method for long-horizon LLM agents that propagates terminal rewards back along the rollout tree and uses forward KL to align the current policy with the target of each turn. According to the original post, on Deep Research this method raises the average accuracy of Qwen3-30B-A3B-Thinking-2507 from 16.23 with GRPO to 21.20.