cs.AI（2025-03-19）

📊 共 13 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) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Do Chains-of-Thoughts of Large Language Models Suffer from Hallucinations, Cognitive Biases, or Phobias in Bayesian Reasoning? 研究表明大型语言模型的思维链在贝叶斯推理中存在幻觉和认知偏差。 large language model chain-of-thought
2 Automated Non-Functional Requirements Generation in Software Engineering with Large Language Models: A Comparative Study 提出一种基于大语言模型的软件非功能需求自动生成框架，提升软件质量。 large language model
3 Foundation models may exhibit staged progression in novel CBRN threat disclosure 利用新型CBRN威胁案例，评估大模型在威胁披露中的阶段性能力 foundation model
4 Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings 首次全面评估DeepSeek模型安全性，揭示其在多风险维度上的脆弱性 large language model foundation model multimodal ✅
5 Prompt engineering and framework: implementation to increase code reliability based guideline for LLMs 提出一种Prompt工程方法，提升LLM生成Python代码的可靠性，降低计算资源消耗。 large language model chain-of-thought
6 R$^2$: A LLM Based Novel-to-Screenplay Generation Framework with Causal Plot Graphs 提出R$^2$框架，利用因果情节图和幻觉感知优化，实现小说到剧本的自动转换。 large language model
7 Probing the topology of the space of tokens with structured prompts 利用结构化提示探究LLM Token空间拓扑结构，揭示其嵌入表示 large language model
8 Reasoning Effort and Problem Complexity: A Scaling Analysis in LLMs 利用Tents puzzle分析LLM推理能力随问题复杂度变化的趋势 large language model
9 Envisioning an AI-Enhanced Mental Health Ecosystem 探索AI增强心理健康生态系统，弥合服务缺口并支持人际互动 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
10 Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models 提出基于众包人类反馈的强化学习框架，提升LLM代码生成能力 reinforcement learning RLHF large language model
11 Reinforcement Learning Environment with LLM-Controlled Adversary in D&D 5th Edition Combat 利用LLM控制的D&D 5E对抗环境提升强化学习智能体策略能力 reinforcement learning large language model
12 World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child 探索类儿童智能：融合物理、神经符号、持续学习等提升AI推理能力 reinforcement learning world model
13 Behaviour Discovery and Attribution for Explainable Reinforcement Learning 提出行为发现与归因框架，提升强化学习决策的可解释性 reinforcement learning offline RL

⬅️ 返回 cs.AI 首页 · 🏠 返回主页