将规划与执行解耦为探索-执行链，以更高效的结构化思维范式突破传统LLM推理瓶颈
arXiv:2509.23946v3 Announce Type: replace-cross Abstract: Many LLMs plan before they act, yet planning and execution are often still entangled in one …
小模型天然具备策略级探索优势，在GRPO中提升多样性比传统token随机更稳定高效
arXiv:2605.30789v1 Announce Type: cross Abstract: We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (G…
用条件信息增益(CIG)驱动智能体探索，为强化学习探索策略提供新思路。
arXiv:2605.20878v1 Announce Type: new Abstract: Intrinsic rewards for exploration in reinforcement learning condition on different contexts: lifelong …