cs.AI（2025-01-20）

📊 共 10 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks	提出SR-FoT框架，提升大语言模型在知识推理任务中的演绎推理能力	large language model chain-of-thought
2	Consolidating TinyML Lifecycle with Large Language Models: Reality, Illusion, or Opportunity?	利用大语言模型简化TinyML生命周期，探索其现实性与机遇	large language model
3	Towards Advancing Code Generation with Large Language Models: A Research Roadmap	提出基于大语言模型的代码生成研究路线图，旨在提升其可靠性、鲁棒性和可用性。	large language model
4	Code Readability in the Age of Large Language Models: An Industrial Case Study from Atlassian	评估LLM生成代码可读性：Atlassian工业案例研究揭示其重要性与可接受度	large language model
5	TutorLLM: Customizing Learning Recommendations with Knowledge Tracing and Retrieval-Augmented Generation	TutorLLM：结合知识追踪与检索增强生成，定制个性化学习推荐	large language model
6	QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks	QualityFlow：基于LLM质量检查的程序合成Agent工作流	large language model
7	Human services organizations and the responsible integration of AI: Considering ethics and contextualizing risk(s)	提出人道服务组织AI责任整合框架，评估风险并促进伦理部署	large language model

#	题目	一句话要点	标签	🔗
8	The impact of intrinsic rewards on exploration in Reinforcement Learning	研究内在奖励多样性对强化学习探索的影响，揭示不同奖励机制在MiniGrid环境下的表现差异。	reinforcement learning representation learning
9	Improving thermal state preparation of Sachdev-Ye-Kitaev model with reinforcement learning on quantum hardware	提出基于强化学习的量子线路优化方法，用于高效制备Sachdev-Ye-Kitaev模型的热态	reinforcement learning	✅
10	Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training	Agent-R：通过迭代自训练提升语言模型Agent的行动反思能力	behavior cloning large language model