cs.AI（2026-04-17）

📊 共 18 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval	综述图与大语言模型及Agent的集成方法，提升推理与检索能力。	large language model multimodal
2	LLM Reasoning Is Latent, Not the Chain of Thought	重新审视LLM推理：潜在状态轨迹而非显式思维链	large language model chain-of-thought
3	Using Large Language Models and Knowledge Graphs to Improve the Interpretability of Machine Learning Models in Manufacturing	利用大语言模型和知识图谱提升机器学习模型在制造业中的可解释性	large language model
4	Structured Abductive-Deductive-Inductive Reasoning for LLMs via Algebraic Invariants	提出基于代数不变性的结构化归纳-演绎-归纳推理框架，提升LLM的逻辑推理能力	large language model chain-of-thought
5	ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams	ReactBench：化学反应图上的MLLM拓扑推理基准测试	large language model multimodal
6	CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval	提出CodeMMR，用于统一检索自然语言、代码和图像的多模态代码信息检索。	multimodal visual grounding
7	Learning to Reason with Insight for Informal Theorem Proving	提出DeepInsightTheorem框架以解决非正式定理证明中的洞察力不足问题	large language model
8	SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems	SocialGrid：用于具身多智能体系统中规划与社会推理的基准测试环境	large language model
9	Neurosymbolic Repo-level Code Localization	提出LogicLoc，结合神经符号推理解决代码库级代码定位中的关键词作弊问题。	large language model
10	Polarization by Default: Auditing Recommendation Bias in LLM-Based Content Curation	研究揭示LLM内容推荐中的极化偏见，并分析不同提示策略和平台的影响	large language model
11	Stein Variational Black-Box Combinatorial Optimization	提出基于Stein变分推理的黑盒组合优化方法，提升复杂问题求解能力。	multimodal
12	HYPERHEURIST: A Simulated Annealing-Based Control Framework for LLM-Driven Code Generation in Optimized Hardware Design	提出基于模拟退火的HYPERHEURIST框架，优化LLM生成硬件设计的功耗、性能和面积。	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	🔗	⭐
13	The Relic Condition: When Published Scholarship Becomes Material for Its Own Replacement	构建学者Bot：从已发表文献中提取推理系统，实现学术功能自动化。	distillation large language model
14	The Price of Paranoia: Robust Risk-Sensitive Cooperation in Non-Stationary Multi-Agent Reinforcement Learning	提出基于策略梯度方差调制的鲁棒多智能体强化学习方法，解决非平稳合作博弈中的不稳定问题。	reinforcement learning
15	Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking	提出AdaRankLLM，通过自适应排序优化检索增强生成，提升效率并过滤噪声。	distillation large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
16	Privacy-Preserving LLMs Routing	提出PPRoute框架，保护用户隐私的同时加速LLM路由过程	MPC large language model
17	DataCenterGym: A Physics-Grounded Simulator for Multi-Objective Data Center Scheduling	提出DataCenterGym，用于多目标数据中心调度的物理仿真环境	MPC model predictive control

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
18	ChemGraph-XANES: An Agentic Framework for XANES Simulation and Analysis	ChemGraph-XANES：用于XANES模拟和分析的Agentic框架，简化工作流程并实现高通量计算。	ASE large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页