突破简单提示，提出改进上下文辅助预测的新策略，让LLM预测更精准
arXiv:2508.09904v3 Announce Type: replace-cross Abstract: Real-world forecasting requires models to integrate not only historical data but also releva…
提出Reward-Swap策略优化，解决多轮对话LLM代理奖励稀疏问题，提升推理与交互效率。
arXiv:2607.04713v1 Announce Type: cross Abstract: Reinforcement learning holds significant potential for training large language models (LLMs) to hand…
新方法STAPO：选择性轨迹感知策略优化，提升LLM智能体训练效率与性能
arXiv:2607.04963v1 Announce Type: new Abstract: Reinforcement Learning (RL) is the dominant paradigm for training Large Language Model (LLM) agents on…
提出一种基于分歧调度的策略自蒸馏方法，有效提升大模型推理训练效果。
arXiv:2607.02502v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) has emerged as a practical method for training large language mod…
用经验数据增强策略优化，大幅提升LLM复杂推理任务的性能和泛化能力。
arXiv:2606.30420v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for improving the reasoni…
新方法Trust Region Masking，通过动态约束策略更新提升大模型长序列强化学习稳定性与收敛性。
arXiv:2512.23075v5 Announce Type: replace-cross Abstract: Policy gradient methods for Large Language Models optimize a policy $\pi_\theta$ via a surro…
大语言模型新优化方法，价值隐式策略优化，高效且稳定。
arXiv:2606.20008v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become a central tool for improving the reasoning a…
全新智能体策略优化方法APPO，推动强化学习前沿发展
arXiv:2606.12384v1 Announce Type: cross Abstract: Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn to…
提出3SPO新方法，以状态分数监督优化LLM智能体策略，提升决策效率和可解释性
arXiv:2606.09961v1 Announce Type: cross Abstract: Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabl…
CATPO方法通过批评增强的树策略优化，显著提升大语言模型推理中的密集奖励获取效率。
arXiv:2606.08346v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving t…
预训练阶段引入强化学习探索，重新审视LLM策略优化方法，带来新训练范式视角。
arXiv:2606.04272v1 Announce Type: new Abstract: The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and sup…
提出软序列策略优化方法，用更平滑的目标函数处理序列决策问题，提升训练稳定性和性能。
arXiv:2602.19327v3 Announce Type: replace-cross Abstract: A significant portion of recent research on Large Language Model (LLM) alignment focuses on …
物理引导的自我蒸馏策略优化，解决LLM后训练中更新步长信任难题，提升模型对齐效果。
arXiv:2606.03620v1 Announce Type: cross Abstract: Self-distilled policy optimization (SDPO) has become a popular paradigm for LLM post-training, where…
新论文提出提示引导的多样化策略优化，提升大语言模型推理的多样性与准确性
arXiv:2606.03021v1 Announce Type: new Abstract: Recent developments in Large Language Models (LLMs) have showcased impressive reasoning capabilities, …
工业级LLM推荐系统中语义与ID空间对齐的Pareto最优策略，直击两个核心瓶颈的权衡方案。
arXiv:2606.03866v1 Announce Type: cross Abstract: Scaling recommender systems via large language models (LLMs) has become a prominent trend in the ind…
无需行为信息就能高效异步训练大模型，ASymPO用不对称规模策略优化让后训练更灵活。
arXiv:2606.03070v1 Announce Type: cross Abstract: Asynchronous reinforcement learning can improve language-model post-training throughput by decouplin…
共进化策略与训练框架，突破传统静态训练瓶颈，实现LLM自主代理强化学习新范式。
arXiv:2606.03108v1 Announce Type: new Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely st…
AI智能体如何让世界模型与策略共同进化？这篇论文提出COMAP框架，实现动态适应而非静态固定，显著提升决策能力。
arXiv:2606.02372v1 Announce Type: new Abstract: Equipping language agents with world models enables them to anticipate environment dynamics and evalua…
混合中长度策略优化实现思维链高效压缩，兼顾性能与成本。
arXiv:2606.01934v1 Announce Type: new Abstract: Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, ye…
用约束策略优化让大模型改写文本以逃逸检测，最新arXiv研究揭秘AI攻防新方法。
arXiv:2606.00392v1 Announce Type: new Abstract: AI-text detectors are vulnerable to paraphrasing and detector-guided paraphrasing attacks, but existin…