cs.CL（2026-11-03）
📊 共 10 篇论文
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (6)
支柱二：RL算法与架构 (RL & Architecture) (3)
支柱一：机器人控制 (Robot Control) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | AdSteer: Native Advertising in Large Language Model Generation | 提出AdSteer框架以解决大语言模型中的原生广告问题 | large language model | ||
| 2 | Evaluating LLMs as Judges of Counterspeech Quality Against Online Hate Speech | 评估大型语言模型在反对网络仇恨言论中的反驳质量 | large language model chain-of-thought | ||
| 3 | From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence | 提出认知共生体以增强人类智能应对AI挑战 | foundation model | ||
| 4 | Who is the Pronoun Pro? Comparing LLMs and Humans at Number-Disambiguation of 'they' | 评估大型语言模型在复杂语言注释中的应用潜力 | large language model | ||
| 5 | When Ground Truth Is Not Ground Truth: Automatic Labeling for Hallucination Detection | 提出自动标注方法以解决大语言模型幻觉检测问题 | large language model | ||
| 6 | ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents | 提出ToolSpace以解决工具中心环境合成的挑战 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | MDSKILL: Learning to Internalize Skill Memory through Multi-View Distillation for Efficient Dynamic Agent Self-Evolution | 提出MDSKILL以解决动态智能体自我进化中的技能记忆内化问题 | reinforcement learning policy learning distillation | ||
| 8 | Shuffled OPSD: When Semantic Consistency Hurts On-Policy Self-Distillation? | 提出Shuffled OPSD以优化在政策自蒸馏中的学习效果 | distillation | ||
| 9 | ReSI-Math: Exploring Recoverable Capability Frontiers for Efficient Reasoning Improvement | 提出ReSI-Math框架以探索可恢复能力边界提升推理效率 | reinforcement learning large language model |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 10 | TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport | 提出TraceRouter++以解决大模型的安全干预问题 | manipulation large language model foundation model |