cs.AI（2026-04-08）

📊 共 22 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Steering the Verifiability of Multimodal AI Hallucinations	提出一种激活空间干预方法，用于控制多模态AI幻觉的可验证性。	large language model multimodal
2	What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning	提出UI-in-the-Loop范式，增强多模态GUI推理中UI元素的理解与交互。	large language model multimodal
3	XR-CareerAssist: An Immersive Platform for Personalised Career Guidance Leveraging Extended Reality and Multimodal AI	XR-CareerAssist：利用扩展现实和多模态AI的沉浸式个性化职业指导平台	multimodal
4	An empirical study of LoRA-based fine-tuning of large language models for automated test case generation	LoRA微调提升大语言模型在自动化测试用例生成中的性能	large language model
5	Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation	提出隐私保护的LLM训练方法以解决文本传输隐私问题	large language model
6	Syntax Is Easy, Semantics Is Hard: Evaluating LLMs for LTL Translation	评估LLM在LTL转换中的能力：语义理解是关键挑战	large language model
7	AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views	AV-SQL：利用Agentic Views分解复杂Text-to-SQL查询，提升执行准确率。	large language model	✅
8	SentinelSphere: Integrating AI-Powered Real-Time Threat Detection with Cybersecurity Awareness Training	SentinelSphere：融合AI威胁检测与网络安全意识培训，提升整体防御能力	large language model
9	Digital Skin, Digital Bias: Uncovering Tone-Based Biases in LLMs and Emoji Embeddings	揭示LLM和Emoji嵌入中基于肤色的偏见，促进AI公平性	large language model
10	Beyond Surface Judgments: Human-Grounded Risk Evaluation of LLM-Generated Disinformation	揭示LLM评估与人类认知偏差：LLM评估失实于LLM生成虚假信息的风险评估	large language model
11	TurboAgent: An LLM-Driven Autonomous Multi-Agent Framework for Turbomachinery Aerodynamic Design	TurboAgent：基于LLM的涡轮机械气动设计自主多智能体框架	large language model
12	Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios	提出CLI-Tool-Bench基准，评估LLM在端到端CLI工具生成中的能力	large language model
13	Restoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approach	提出基于LLM的社会模拟受众分割方法，提升异质性建模能力	large language model
14	AI-Driven Research for Databases	提出一种AI驱动的数据库研究方法，通过协同进化评估器与解决方案，实现数据库性能的自动优化。	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	🔗	⭐
15	Energy Saving for Cell-Free Massive MIMO Networks: A Multi-Agent Deep Reinforcement Learning Approach	提出基于多智能体深度强化学习的节能方案，用于蜂窝自由大规模MIMO网络。	reinforcement learning deep reinforcement learning
16	KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning	提出KD-MARL，通过知识蒸馏实现多智能体强化学习在资源受限环境下的高效部署。	reinforcement learning distillation
17	Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach	提出基于归纳逻辑编程的后验方法，解释偏好学习中的神经网络。	preference learning
18	Strategic Persuasion with Trait-Conditioned Multi-Agent Systems for Iterative Legal Argumentation	提出基于特质条件多智能体系统的策略性说服框架，用于迭代法律论证。	reinforcement learning large language model
19	EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration	EmoMAS：基于贝叶斯编排的情感感知多智能体高风险边缘协商系统	reinforcement learning large language model
20	Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability	重新审视推理SFT中的泛化能力：优化、数据和模型能力的条件分析	reinforcement learning chain-of-thought
21	How Much LLM Does a Self-Revising Agent Actually Need?	通过外部化Agent状态，研究LLM在自修正Agent中的作用	world model world models

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
22	Riemann-Bench: A Benchmark for Moonshot Mathematics	提出Riemann-Bench，用于评估AI在研究级数学问题上的推理能力	IMoS

⬅️ 返回 cs.AI 首页 · 🏠 返回主页