cs.AI（2026-09-16）

📊 共 23 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14) 支柱一：机器人控制 (Robot Control) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱四：生成式动作 (Generative Motion) (1)

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

#题目一句话要点标签🔗⭐
1 Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents 提出SynAgent框架以解决自驱动实验室决策透明性问题 large language model multimodal
2 Faithful yet Collusive: Why Chain-of-Thought Monitoring Cannot Detect Collusion in LLM Pricing Agents under Oligopolistic Competition 提出因果图分歧框架以检测LLM定价代理的合谋行为 large language model chain-of-thought
3 Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models 提出狡猾数据以增强大型语言模型的安全警觉性 large language model
4 Cultural Competence in Context: A Large Language Model Passes the Turing Test in Finland 提出基于角色提示的Turing测试方法以评估语言模型的文化适应性 large language model
5 GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models 提出GYROval基准以评估大语言模型的文化价值取向 large language model
6 WFM: Wiki Foundation Model for Complex Agentic Reasoning 提出WFM以解决复杂代理推理中的知识表示问题 foundation model
7 An Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks 评估成本效益的语言模型在算法编程任务中的应用 large language model
8 Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning 提出Mahalanobis-Ensemble解码以优化LLM候选令牌选择 large language model
9 Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum 提出agentic-eCAL以优化边缘云环境中的智能体AI能耗与内存管理 large language model
10 Clueing up LLMs with Tool-Augmented Deductive Reasoning 提出工具增强的推理方法以提升LLMs的逻辑推理能力 large language model
11 Which LLM is Best for Translating Natural Language Goals to PDDL 提出基于LLM的自然语言目标到PDDL翻译方法 large language model
12 Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making 提出递归推理与统计外推的区分方法以优化多智能体决策 large language model
13 Who Audits Whom, on What Substrate, with What Evidence? An Independence-Graded Audit Protocol for Agentic AI 提出独立性分级审计协议以解决代理AI审计问题 foundation model
14 AutoTuneBench: Trustworthy Measurement for Agent Auto-Tuning of LLM Serving Engines 提出AutoTuneBench以解决LLM服务引擎自动调优的测量可信性问题 large language model

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
15 Risk-Aware World Modeling with Flow-Guided Occupancy Evolution for Selective Trajectory Planning in Automated Driving 提出风险感知世界建模框架以解决自动驾驶中的轨迹规划问题 motion planning world model world models
16 Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents 提出市场信号注入以操控LLM定价代理的行为 manipulation large language model
17 WetRobo: A Reproducible Robot Kit for Coding Agents in Biological Laboratories WetRobo：一种可重复使用的机器人套件以简化生物实验室的自动化 teleoperation vision-language-action VLA ✅
18 Symbolic Temporal Supervision of LLM Agents Using Contracts 提出ContrAgent框架以解决LLM代理的安全性问题 manipulation 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🔗⭐
19 Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning 提出PIVOT框架以解决视觉基础多模态推理中的优化瓶颈问题 reinforcement learning multimodal
20 Missing Bridges: Composition-Aware Active Imitation Learning 提出AALT以解决多任务学习中的示范请求问题 imitation learning diffusion policy
21 What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models 系统性映射棋类研究以探讨战略推理 reinforcement learning large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
22 Multimodal Conditioning of Fine-Tuned Stable Diffusion XL for Controllable and Culturally Faithful Ulos Motif Generation 提出多模态生成框架以解决传统巴塔克乌洛斯图案设计问题 semantic map large language model multimodal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
23 PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs 提出PentestChain框架以降低自动渗透测试成本 penetration

⬅️ 返回 cs.AI 首页 · 🏠 返回主页