cs.AI（2025-03-13）

📊 共 20 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16 🔗3) 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) (16 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Learning to Inference Adaptively for Multimodal Large Language Models	AdaLLaVA：针对多模态大语言模型的自适应推理框架，优化资源受限场景下的性能	large language model multimodal	✅
2	ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning	ImageScope：通过大模型集体推理统一语言引导的图像检索任务	multimodal chain-of-thought
3	SurgRAW: Multi-Agent Workflow with Chain-of-Thought Reasoning for Surgical Intelligence	SurgRAW：基于CoT多智能体工作流，提升手术智能任务性能	chain-of-thought
4	Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overview	软件漏洞检测：形式化验证、大语言模型与混合方法综述	large language model
5	Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search	Tempest：利用树搜索实现大语言模型的多轮自主越狱	large language model
6	Siamese Foundation Models for Crystal Structure Prediction	提出Siamese结构的晶体结构预测基础模型DAO，显著提升晶体材料发现效率。	foundation model
7	Uncertainty in Action: Confidence Elicitation in Embodied Agents	提出具身智能体置信度评估框架，解决开放多模态环境中不确定性问题	multimodal chain-of-thought
8	Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data	Chat-TS：增强LLM在时序数据和自然语言上的多模态推理能力	large language model multimodal
9	Empirical Computation	探索经验计算：一种基于经验而非形式化方法的计算范式	large language model
10	CUBETESTERAI: Automated JUnit Test Generation using the LLaMA Model	CUBETESTERAI：利用LLaMA模型自动化生成Java JUnit测试用例，提升代码覆盖率。	large language model
11	FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAG	提出FG-RAG，通过上下文感知的细粒度图RAG增强查询聚焦的摘要生成	large language model	✅
12	LLM Agents Display Human Biases but Exhibit Distinct Learning Patterns	研究表明LLM在经验决策中表现出与人类相似的偏差，但学习模式迥异	large language model
13	From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution	提出基于结构-功能协同进化的无模板算法设计框架，超越人工专家。	large language model
14	StepMathAgent: A Step-Wise Agent for Evaluating Mathematical Processes through Tree-of-Error	提出StepMathAgent，通过错误树评估数学过程，提升LLM数学能力评估的准确性和可解释性。	large language model	✅
15	LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems	探索LLM多智能体系统构建技术：架构、记忆、规划与框架	large language model
16	OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM	提出OR-LLM-Agent，利用推理LLM自动建模和解决运筹学优化问题。	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	🔗	⭐
17	H2-MARL: Multi-Agent Reinforcement Learning for Pareto Optimality in Hospital Capacity Strain and Human Mobility during Epidemic	提出H2-MARL，用于疫情期间医院容量压力和人类流动性的帕累托最优多智能体强化学习。	reinforcement learning spatiotemporal
18	Adaptive Preference Aggregation	提出自适应偏好聚合策略，提升AI对人类价值观的对齐效果	reinforcement learning RLHF foundation model
19	Reinforcement Learning and Life Cycle Assessment for a Circular Economy -- Towards Progressive Computer Science	探索强化学习与生命周期评估在循环经济中的应用，借鉴计算机象棋的成功经验。	reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	Graph-Grounded LLMs: Leveraging Graphical Function Calling to Minimize LLM Hallucinations	提出Graph-Grounded LLMs，利用图函数调用减少LLM在图任务中的幻觉	motion planning scene understanding large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页