智能体历史记录膨胀是部署大痛点，AgentOCR用光学自压缩给记忆瘦身，值得一看。
arXiv:2601.04786v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) enable agentic systems trained with reinforc…
单层Transformer训练竟能媲美全参数强化学习？突破性发现重塑参数效率认知。
arXiv:2607.01232v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a central component of post-training large language models (LLM…
针对RL训练推理模型普遍存在的“过度思考”问题，提出动态rollout编辑方法，有效提升推理效率与准确性。
arXiv:2606.17890v1 Announce Type: new Abstract: Long-form chain-of-thought reasoning can improve LLM performance on complex tasks, but models often co…
LLM也能当训练环境设计师？这篇论文提出LLM-as-Environment，自动为RL生成多智能体训练环境，终结手工调参。
arXiv:2606.17682v1 Announce Type: new Abstract: Reinforcement learning pipelines for Large Language Model (LLM) training often rely on manually redesi…
提出在线验证提示选择方法，大幅提升大推理模型RL训练效率
arXiv:2603.25184v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in…
探索智能体工具调用与强化学习训练的效率与效果，为AI应用落地提供关键洞见。
arXiv:2606.00135v1 Announce Type: new Abstract: Tool-calling is a central component of modern large language model (LLM) agents, equipping them with s…
外推权重平均法揭示了代码强化学习中正确性与效率的权衡前沿，为模型调优提供新视角。
arXiv:2605.28751v1 Announce Type: cross Abstract: Linear interpolation between fine-tuned checkpoints has been shown to trace the Pareto front between…
超越正确性：通过强化学习调和过程与结果奖励，为模型训练提供新视角
arXiv:2509.03403v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning …