cs.AI（2026-01-21）

📊 共 18 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11) 支柱一：机器人控制 (Robot Control) (6) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Evaluation of Large Language Models in Legal Applications: Challenges, Methods, and Future Directions 综述：评估大语言模型在法律应用中的挑战、方法与未来方向 large language model
2 Benchmarking Large Language Models for ABAP Code Generation: An Empirical Study on Iterative Improvement by Compiler Feedback 评估大语言模型在ABAP代码生成中的性能，着重分析编译器反馈的迭代改进效果 large language model
3 Visual and Cognitive Demands of a Large Language Model-Powered In-vehicle Conversational Agent 评估LLM车载对话代理的视觉和认知负荷，支持安全部署。 large language model
4 IB-GRPO: Aligning LLM-based Learning Path Recommendation with Educational Objectives via Indicator-Based Group Relative Policy Optimization 提出IB-GRPO，通过指标引导对齐LLM学习路径推荐与教学目标 large language model
5 How to Build AI Agents by Augmenting LLMs with Codified Human Expert Domain Knowledge? A Software Engineering Framework 提出一种软件工程框架，通过增强LLM实现领域专家知识驱动的AI Agent构建 large language model
6 The Plausibility Trap: Using Probabilistic Engines for Deterministic Tasks 提出工具选择工程以解决概率引擎在确定性任务中的低效问题 large language model
7 The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution 提出基于Agentic Attribution的框架，用于理解LLM Agent行为背后的驱动因素。 large language model
8 When Text-as-Vision Meets Semantic IDs in Generative Recommendation: An Empirical Study 提出基于OCR的文本表示方法，提升生成式推荐中语义ID学习效果 multimodal
9 HCVR Scene Generation: High Compatibility Virtual Reality Environment Generation for Extended Redirected Walking 提出HCVR框架，为扩展重定向行走生成高兼容性虚拟现实环境 large language model
10 GEGO: A Hybrid Golden Eagle and Genetic Optimization Algorithm for Efficient Hyperparameter Tuning in Resource-Constrained Environments 提出GEGO混合算法，用于资源受限环境下的高效超参数调优 multimodal
11 HELIOS: Hierarchical Graph Abstraction for Structure-Aware LLM Decompilation HELIOS：一种用于结构感知LLM反编译的分层图抽象方法 large language model

🔬 支柱一：机器人控制 (Robot Control) (6 篇)

#题目一句话要点标签🔗⭐
12 BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries 提出BayesianVLA以解决视觉语言行动模型的泛化问题 manipulation vision-language-action VLA
13 Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation 揭示LLM评估中链式思维的脆弱性及其影响 manipulation large language model chain-of-thought
14 Proximal Policy Optimization with Evolutionary Mutations 提出POEM算法，通过进化变异增强PPO探索能力，解决强化学习早熟收敛问题。 bipedal biped reinforcement learning
15 CI4A: Semantic Component Interfaces for Agents Empowering Web Automation 提出CI4A以解决Web组件操作的低效问题 manipulation reinforcement learning large language model
16 NeuroFilter: Privacy Guardrails for Conversational LLM Agents NeuroFilter：为对话式LLM Agent提供隐私保护，降低计算成本。 manipulation large language model
17 An Agentic Operationalization of DISARM for FIMI Investigation on Social Media 提出基于Agent的DISARM框架，用于大规模社交媒体上的FIMI调查 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
18 Vehicle Routing with Finite Time Horizon using Deep Reinforcement Learning with Improved Network Embedding 提出一种改进网络嵌入的深度强化学习方法，解决有限时间范围内的车辆路径问题。 reinforcement learning deep reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页