用稠密层次奖励与课程学习提升代码大模型训练效果，为AI编程能力突破提供新路径。
arXiv:2607.26457v1 Announce Type: new Abstract: Reinforcement learning is a natural post-training paradigm for code-oriented large language models bec…
提出“思维策略”框架，通过在线策略进化实现测试时训练，打破冻结策略限制，显著提升大模型复杂推理能力。
arXiv:2601.20379v2 Announce Type: replace Abstract: Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caus…
预训练课程让微调更精准，揭秘选择性微调的新思路。
arXiv:2607.04846v1 Announce Type: cross Abstract: Transformers follow implicit curricula whereby some tasks are learned before others. However, how ex…
直击空间相关数据建模的“性能幻觉”，用结构感知分层分区与课程式分布鲁棒优化，为泛化性提供新解。
arXiv:2607.02055v1 Announce Type: cross Abstract: Performance evaluation in AI systems commonly assumes that random dataset splits produce independent…
课程强化学习能否突破基础模型推理上限？这项研究给出新答案。
arXiv:2606.22317v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is widely viewed as a promising path toward co…
LaBSE搭配渐进式课程学习，精准捕捉多元文化中的极化信号，ACL 2026亮点研究。
arXiv:2606.21718v1 Announce Type: cross Abstract: Detecting online polarization remains a critical challenge, particularly in multilingual and multicu…
分阶段训练课程提升排序与分配任务的鲁棒性，构建渐进式表征学习策略。
arXiv:2606.09891v1 Announce Type: cross Abstract: Ranking in digital marketplaces is a dynamic exposure-allocation mechanism: displayed items shape di…
从易到难课程驱动模型自我迭代，任务中心理论揭示高效训练新路径。
arXiv:2602.10014v3 Announce Type: replace Abstract: Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verif…
动态调整数据与模型匹配度，让知识蒸馏更贴合学生能力，提升推理模型微调效率。
arXiv:2605.29229v1 Announce Type: new Abstract: Reasoning distillation transfers complex reasoning abilities from large language models (LLMs) to smal…
两阶段课程后训练让LLM学会在图数据中探索和推理，创新训练方法带来更强推理能力。
arXiv:2602.02518v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly rely on external knowledge to improve factuality, …
揭秘训练数据对RL记忆体的课程效应，实证研究记忆增强QA中的性能提升关键。
arXiv:2605.23067v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a viable recipe for training LLM agents to reason over exte…
用自定进度课程学习平衡多模态对话中的情感识别，提升模型在复杂互动场景中的表现。
arXiv:2605.21565v1 Announce Type: new Abstract: Multimodal Emotion Recognition in Conversations (MERC) is a crucial task for understanding human inter…
将推理链分解为可验证子问题，用课程强化学习精准分配LLM推理中的信用，突破训练瓶颈。
arXiv:2605.22074v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) has shown strong promise for LLM reasoning, bu…