cs.AI（2026-01-09）

📊 共 22 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) (13) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Cedalion Tutorial: A Python-based framework for comprehensive analysis of multimodal fNIRS & DOT from the lab to the everyday world Cedalion：一个用于全面分析多模态fNIRS/DOT数据的Python框架 multimodal
2 Crisis-Bench: Benchmarking Strategic Ambiguity and Reputation Management in Large Language Models Crisis-Bench：评估大语言模型在危机公关中的战略模糊与声誉管理能力 large language model
3 Understanding LLM-Driven Test Oracle Generation 利用大语言模型生成测试预言，解决软件测试中的预言问题 large language model foundation model
4 ART: Adaptive Reasoning Trees for Explainable Claim Verification 提出自适应推理树ART，用于可解释的声明验证 large language model chain-of-thought
5 Safety Not Found (404): Hidden Risks of LLM-Based Robotics Decision Making 揭示LLM机器人决策的潜在风险：安全关键场景下的灾难性错误 large language model
6 Explainable AI: Learning from the Learners 结合可解释AI与因果推理，从AI学习者中提取知识 foundation model
7 Can AI mediation improve democratic deliberation? 探讨AI调解能否提升民主审议质量，关注LLM在促进共识中的作用 large language model
8 Decoding Workload and Agreement From EEG During Spoken Dialogue With Conversational AI 探索脑机接口在人机对话中的应用：利用脑电信号解码工作负荷与一致性 large language model
9 DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation DynaDebate：动态路径生成的多智能体辩论框架，打破同质化推理 large language model
10 Logic-Parametric Neuro-Symbolic NLI: Controlling Logical Formalisms for Verifiable LLM Reasoning 提出逻辑可控的神经符号自然语言推理框架，提升LLM推理的鲁棒性和适应性 large language model
11 RISE: Rule-Driven SQL Dialect Translation via Query Reduction RISE：通过查询简化实现规则驱动的SQL方言翻译 large language model
12 The Evaluation Gap in Medicine, AI and LLMs: Navigating Elusive Ground Truth & Uncertainty via a Probabilistic Paradigm 提出基于概率范式的评估方法，解决医学AI和LLM中ground truth不确定性问题 large language model
13 STELP: Secure Transpilation and Execution of LLM-Generated Programs STELP：安全转译与执行LLM生成代码，保障AI系统安全 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
14 Open World Knowledge Aided Single-Cell Foundation Model with Robust Cross-Modal Cell-Language Pre-training 提出OKR-CELL，利用开放世界知识增强单细胞多模态预训练，提升模型鲁棒性。 contrastive learning curriculum learning large language model
15 Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection 提出基于强化学习的大语言模型信用卡欺诈检测方法，提升可解释性。 reinforcement learning large language model
16 Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning 提出iMIST：一种基于强化学习的迭代式工具伪装攻击方法，用于破解大型语言模型 reinforcement learning large language model
17 TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents 提出TowerMind，一个轻量级、多模态的塔防游戏环境，用于评估LLM智能体。 reinforcement learning PPO large language model ✅
18 CHDP: Cooperative Hybrid Diffusion Policies for Reinforcement Learning in Parameterized Action Space 提出CHDP框架，通过合作式混合扩散策略解决参数化动作空间强化学习问题 reinforcement learning diffusion policy
19 StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management StackPlanner：具任务经验记忆管理的分层集中式多智能体系统 reinforcement learning large language model
20 WildSci: Advancing Scientific Reasoning from In-the-Wild Literature WildSci：提出一个从真实科研文献中自动合成的科学推理数据集，用于提升LLM在科学领域的推理能力。 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🔗⭐
21 Open-Vocabulary 3D Instruction Ambiguity Detection 提出Ambi3D基准和AmbiVer框架，解决开放词汇3D指令歧义检测问题 open-vocabulary open vocabulary embodied AI ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 Evaluating the Use of LLMs for Automated DOM-Level Resolution of Web Performance Issues 评估大型语言模型在自动化DOM层级Web性能问题解决中的应用 manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页