cs.AI（2026-02-26）

📊 共 34 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) (24 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 SPM-Bench: Benchmarking Large Language Models for Scanning Probe Microscopy SPM-Bench：针对扫描探针显微镜的大语言模型权威自动评测基准 large language model multimodal
2 Multi-Agent Large Language Model Based Emotional Detoxification Through Personalized Intensity Control for Consumer Protection 提出基于多Agent LLM的情绪解毒系统MALLET，以个性化强度控制保护消费者免受过度情绪刺激。 large language model
3 SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation SC-Arena：面向单细胞推理的自然语言基准，采用知识增强评估 large language model foundation model
4 Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction 评估小语言模型在领导者-跟随者交互中的零样本和单样本自适应能力 large language model
5 AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications 提出AMA-Bench评估Agent在长时程记忆应用中的性能，并提出AMA-Agent提升效果。 large language model
6 CourtGuard: A Model-Agnostic Framework for Zero-Shot Policy Adaptation in LLM Safety CourtGuard：一种零样本策略适应的LLM安全模型无关框架 large language model
7 Utilizing LLMs for Industrial Process Automation 利用大型语言模型加速工业过程自动化软件开发 large language model
8 Mitigating Legibility Tax with Decoupled Prover-Verifier Games 提出解耦的证明者-验证者博弈，缓解大模型输出可验证性与准确性之间的权衡问题。 large language model
9 A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring 提出决策理论视角的隐写术以解决LLM监控问题 large language model
10 Enhancing CVRP Solver through LLM-driven Automatic Heuristic Design 提出基于LLM的自动启发式算法设计AILS-AHD，提升CVRP求解器性能 large language model
11 LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure LLMServingSim 2.0：异构和解耦LLM Serving基础设施的统一模拟器 large language model
12 Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search 提出CC-BOS框架，利用文言文和果蝇优化算法实现大语言模型的黑盒越狱攻击。 large language model
13 Discovery of Interpretable Physical Laws in Materials via Language-Model-Guided Symbolic Regression 提出语言模型引导的符号回归，用于发现材料科学中可解释的物理定律 large language model
14 MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks MiroFlow：面向通用深度研究任务的高性能鲁棒开源Agent框架 large language model
15 Distributed LLM Pretraining During Renewable Curtailment Windows: A Feasibility Study 提出基于可再生能源消纳窗口的分布式LLM预训练方法 large language model
16 AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification AgentSentry：通过时序因果诊断和上下文净化缓解LLM Agent中的间接提示注入攻击 large language model
17 IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation IMMACULATE：一种通过可验证计算实现LLM审计的实用框架 large language model ✅
18 Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions 综述：面向个性化LLM驱动Agent，探讨其基础、评估及未来方向 large language model
19 MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios 提出 MobilityBench，用于评估真实世界出行场景下的路线规划Agent large language model ✅
20 Addressing Climate Action Misperceptions with Generative AI 利用生成式AI解决气候行动认知偏差，提升环保行为意愿 large language model
21 Requesting Expert Reasoning: Augmenting LLM Agents with Learned Collaborative Intervention 提出AHCE框架，通过学习协作干预增强LLM Agent在专业领域的推理能力 large language model
22 Generative Agents Navigating Digital Libraries Agent4DL：利用生成式Agent模拟数字图书馆用户搜索行为 large language model
23 Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents 利用认知模型和AI算法为语言智能体设计提供模板 large language model
24 Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search 提出CC-BOS框架，利用文言文和果蝇优化算法实现大语言模型的黑盒越狱攻击。 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🔗⭐
25 FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning 提出FactGuard以解决视频虚假信息检测中的推理不足问题 reinforcement learning large language model multimodal
26 RLHFless: Serverless Computing for Efficient RLHF 提出RLHFless，利用Serverless计算高效训练RLHF，提升资源利用率并降低成本。 reinforcement learning RLHF large language model
27 The Trinity of Consistency as a Defining Principle for General World Models 提出通用世界模型的“一致性三位一体”原则，并构建多帧推理与生成基准CoW-Bench。 world model multimodal
28 Agentic AI for Intent-driven Optimization in Cell-free O-RAN 提出Agentic AI框架，用于Cell-free O-RAN中意图驱动的优化，提升资源利用率。 reinforcement learning deep reinforcement learning DRL
29 Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive 揭示基于优化的AI系统在规范响应上的局限性，提出架构性约束条件。 reinforcement learning RLHF large language model
30 QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning QSIM：通过动作相似性加权Q学习缓解多智能体强化学习中的过度估计 reinforcement learning ✅
31 Automated Vulnerability Detection in Source Code Using Deep Representation Learning 提出基于卷积神经网络的源代码漏洞自动检测方法，提升C语言漏洞检测召回率。 representation learning
32 Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space 提出L-HAKT，利用LLM和双曲空间对齐学生行为，提升知识追踪效果 contrastive learning large language model
33 Learning to Generate Secure Code via Token-Level Rewards 提出Vul2Safe框架，通过token级奖励学习生成安全代码，解决安全数据稀缺和奖励信号粗糙问题。 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
34 The AI Research Assistant: Promise, Peril, and a Proof of Concept 利用人机协作发现Hermite求积法则的新误差表示和界限 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页