cs.AI（2026-07-07）

📊 共 30 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (21) 支柱二：RL算法与架构 (RL & Architecture) (9)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models 提出RMISC数据集以提升时间序列基础模型的泛化能力 foundation model
2 SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation 提出SearchEyes以解决多模态搜索智能中的结构性断裂问题 multimodal
3 Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents 提出统一分类法以解决大型语言模型代理的工具使用与推理失败问题 large language model
4 Synthetic Consumer Insight Generation with Large Language Models 利用大型语言模型生成合成消费者洞察以解决数据收集难题 large language model
5 Integrating knowledge graphs and multilingual scholarly corpora for domain-adaptive LLMs in SSH 提出知识图谱与多语言学术语料库整合以适应社会科学与人文学科的LLM large language model foundation model
6 UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation 提出UI2App以解决可执行Web应用生成中的交互推断问题 large language model
7 Rethinking Indic AI from a Lens of Cultural Heritage Preservation 提出文化感知方法以解决印度语言AI模型的资源与表现问题 foundation model
8 Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade 提出基于回忆控制探针级联的早期中止机制以优化LLM代理任务 large language model
9 An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery 提出实验设计框架以评估自主模型发现的智能体AI large language model
10 TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting 提出TopoBrick框架以解决建筑物IoT预测中的变量选择问题 foundation model
11 Harnessing Code Agents for Automatic Software Verification 提出代码代理以实现自动软件验证 large language model
12 DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail 提出DT-Guard以解决大语言模型安全性问题 large language model
13 From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution 提出一种新框架以实现异构AI的内生演化 large language model
14 PolyWorkBench: Benchmarking Multilingual Long-Horizon LLM Agents 提出PolyWorkBench以评估多语言长时程LLM代理的性能 large language model
15 AgoraSim: A Hybrid Agent-Based Modeling Framework 提出AgoraSim以解决社交场景模拟的比较与分析问题 multimodal
16 Auto-DSM Under the Lens: A Black-Box Evaluation Framework for LLM-Based DSM Generation 提出黑箱评估框架以评估LLM生成设计结构矩阵能力 large language model
17 From Textural Counterpoint to Feature Encoding: A Multi-Dimensional Machine Representation Study of Haydn's "The Lark" Integrating Electroacoustic Analysis 提出一种新方法以解决多声部音乐生成模型的角色感知不足问题 TAMP
18 Uncovering Latent Depression Severity for Binary Depression Detection via Advantage-weighting Ranking 提出二元优势加权排序损失以解决抑郁检测问题 multimodal
19 i-EXAM: Instructable and Explainable Attack Connectivity Graph Modeler 提出i-EXAM以帮助网络安全管理与攻击路径分析 large language model
20 Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis 研究同源LLM的拒绝行为对安全分析的影响 large language model
21 Controlling Tool Use with Heading-Specific Activation Steering 提出工具使用控制方法以优化大型语言模型的工具调用 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
22 CMDR: Contextual Multimodal Document Retrieval 提出CMDR以解决多模态文档检索中的上下文建模问题 contrastive learning multimodal
23 A Definition and Roadmap for World Models 提出世界模型的科学定义与发展路线图 reinforcement learning world model world models
24 Multi-Agent Deep Reinforcement Learning for Multi Objective Battery Management in Dairy Farms 提出多智能体深度强化学习以优化奶牛场电池管理 reinforcement learning deep reinforcement learning
25 Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning 提出AgenticAI-Supervisor以解决传统评估在多步决策中的不足 reinforcement learning reward shaping large language model
26 SCOReD: Student-Aware CoT Optimization for Recommendation Distillation 提出SCOReD以解决推荐领域的CoT蒸馏问题 distillation chain-of-thought
27 Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents 提出基于信息增益的回滚策略优化以提升多回合LLM代理性能 reinforcement learning policy learning large language model
28 Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment 提出VAORA以解决视觉语言模型的物理推理泛化问题 reward design chain-of-thought
29 ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation 提出ArtisanCAD以解决工业级CAD生成中的模糊性问题 distillation
30 TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training 提出TurnOPD以解决长时间跨度代理训练中的低效问题 distillation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页