AI Agent AI工具 ALFWorld API-calling agent AReaL AWM Adaptive Supervision Agent Agent Infra Agent-World AgentFounder Agentic CPT Agentic Discovery Agentic RL Black-Box Distillation Claude Code Computer Use Continual Learning Continual Pre-training Credit Assignment DAPO DARE DASH Deep Research DynaWeb EWC Echo Trap Environment Synthesis Forward KL GDPO GLM-4.5 GLM-5.3 GPT-6 Astra GRPD GRPO GSPO ICLR 2026 ICML 2026 Jev Kimi K3 LLM LLM Infra LLM as world model Latent Reasoning LoRA Long-Horizon Long-Horizon Agent MCP MOPD Meta-Learning MoE Model Merging Model-Based RL Multi-Turn RL NGU Neural Computer OPD OPDVR OPSD On-Policy Distillation On-Policy-Distillation On-policy Distillation OpenAI PPO Planning Post-Training Prompt Engineering R-WoM RAG RAGEN REINFORCE RL RLCD RLHF RLVR Recursive Self-Improvement Retrieval-Augmented World Model SETA SFT SMOPD SOPD Scaling Law Schmidhuber Self-Evolution StarPO Step-Level Supervision Synaptic Intelligence TIES-Merging Task Arithmetic Test-Time RL Test-Time Training Test-time Compute Token Reweighting Tokenizer Transformer TypeSafe VLA VLM Video Model WAM Web Agent World Model agentic RL agentic environment agentic flow agentic scaling agentic search attention continual learning continual reinforcement learning credit assignment curriculum curriculum learning data synthesis environment evolution environment simulation environment synthesis flow matching function calling generative teaching graph hindsight instruction tuning long horizon model collapse model-based reinforcement learning multi-timescale planning process reward retriever training rollout self-evolution self-training slime survey synthetic data terminal agent text world model token-level tool use tool-use agent value function value-free verifiable reward verified environment verl web agent world model 专家模型迭代 世界模型 代码生成 优势估计 信息流 信用分配 具身智能 内在维度 分层强化学习 分布式训练 动态采样 参数正则化 可执行代码 可解释性 后训练 基座模型 基模后训练 基础模型 多奖励优化 多教师蒸馏 多模态 大模型推理 奖励塑形 奖励门控 宏动作 对齐 工具使用 工程实践 开发工具 异步训练 强化学习 影响函数 技术报告 推理 推理时计算 推理模型 推理系统 推理退化 数据合成 数据预处理 方差缩减 智能体 机器人 机器人学习 概率校准 模型压缩 模型训练 模型评估 混合推理 灾难性遗忘 物理推理 监督微调 知识蒸馏 科学推理 稀疏奖励 组合泛化 细粒度奖励 网络安全 自动化 自蒸馏 表征几何 计算范式 记忆训练 论文清单 论文精读 论文综述 课程学习 软件架构 长上下文 长程任务 长程推理 预训练 验证器