Trending

arXiv:2606.24064

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

Bei Li·Jingang Wang·Tianyuan Shi·Canbin Huang·Xiaojun Quan·Qifan Wang·Xin Chen

Jun 23, 2026submitted

132citations

View PDF arXiv page Code4.1k

Preview of Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

TL;DR

AI-GENERATED

State-of-the-art research on Beyond Trajectory Imitation: Strategy-Gu achieving benchmark breakthroughs.

TASKS

METHODS

Related Papers