cs.AI（2025-09-17）
📊 共 4 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Reasoning Efficiently Through Adaptive Chain-of-Thought Compression: A Self-Optimizing Framework | 提出SEER自优化框架，通过自适应压缩CoT推理链提升LLM在软件工程任务中的效率与准确率。 | large language model chain-of-thought | ||
| 2 | See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles | 提出StaR方法，提升多模态Agent在GUI交互中Toggle控制的准确性 | multimodal | ✅ | |
| 3 | A Taxonomy of Prompt Defects in LLM Systems | 构建LLM系统提示词缺陷分类体系，提升LLM应用可靠性 | large language model |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning | THOR：基于强化学习的工具集成层次优化，用于数学推理 | manipulation large language model | ✅ |