cs.AI（2026-03-13）

📊 共 19 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) (14 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Beyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation 提出CRYSTAL基准，用于评估多模态推理的可解释性和中间步骤正确性。 multimodal
2 VLM4Rec: Multimodal Semantic Representation for Recommendation with Large Vision-Language Models VLM4Rec：利用大型视觉-语言模型进行多模态语义表征的推荐 multimodal ✅
3 Multiscale Structure-Guided Latent Diffusion for Multimodal MRI Translation 提出MSG-LDM，通过多尺度结构引导潜在扩散模型实现多模态MRI图像转换，提升解剖一致性和纹理细节。 multimodal ✅
4 Developing the PsyCogMetrics AI Lab to Evaluate Large Language Models and Advance Cognitive Science -- A Three-Cycle Action Design Science Study 构建PsyCogMetrics AI实验室，用于评估大型语言模型并推进认知科学研究 large language model
5 Semantic Invariance in Agentic AI 提出基于变质测试的框架，评估LLM智能体在语义不变性下的推理鲁棒性 large language model foundation model
6 Early Pruning for Public Transport Routing 提出Early Pruning加速公共交通路径规划，提升RAPTOR算法效率。 multimodal
7 From Experiments to Expertise: Scientific Knowledge Consolidation for AI-Driven Computational Research QMatSuite平台通过知识积累提升AI驱动的计算材料研究效率与准确性 large language model
8 Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning Delta1与LLM结合，实现可信且可解释的神经符号推理 large language model
9 Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization 提出AMRO-S，通过蚁群优化实现高效且可解释的多智能体LLM路由 large language model
10 Human-Centered Evaluation of an LLM-Based Process Modeling Copilot: A Mixed-Methods Study with Domain Experts 人本评估LLM流程建模助手：领域专家混合方法研究 large language model
11 ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning ToolTree：通过双重反馈蒙特卡洛树搜索和双向剪枝实现高效的LLM Agent工具规划 large language model
12 Seeing Eye to Eye: Enabling Cognitive Alignment Through Shared First-Person Perspective in Human-AI Collaboration Eye2Eye：通过共享第一人称视角实现人机协作中的认知对齐 multimodal
13 The Economics of AI Supply Chain Regulation 通过博弈论模型分析AI供应链监管政策对消费者剩余的影响 foundation model
14 Towards unified brain-to-text decoding across speech production and perception 提出统一的脑到文本解码框架以解决多模态语言理解问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
15 ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning ARL-Tangram：通过细粒度资源管理提升Agentic强化学习的资源效率 reinforcement learning large language model
16 Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation 提出结构化蒸馏方法，用于个性化Agent记忆压缩，实现11倍Token缩减并保留检索能力。 distillation
17 Mask2Flow-TSE: Two-Stage Target Speaker Extraction with Masking and Flow Matching 提出Mask2Flow-TSE，结合掩码与流匹配实现高质量目标说话人提取 flow matching
18 Context is all you need: Towards autonomous model-based process design using agentic AI in flowsheet simulations 提出基于Agentic AI的流程模拟自主模型设计框架，提升化学流程建模效率。 distillation large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
19 LLM Constitutional Multi-Agent Governance 提出宪法多智能体治理框架，保障LLM影响下的合作伦理稳定，避免操纵。 manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页