cs.AI（2025-02-10）

📊 共 5 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning	提出无害版权保护方法以解决知识库被滥用问题	large language model chain-of-thought
2	Scalable and Ethical Insider Threat Detection through Data Synthesis and Analysis by LLMs	利用LLM合成数据与分析，实现可扩展且符合伦理的内部威胁检测	large language model
3	SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering	SyncMind：衡量协同软件工程中Agent的失步恢复能力	large language model	✅
4	LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks	LessLeak-Bench：首次大规模评估LLM在软件工程基准测试中的数据泄露问题	large language model

#	题目	一句话要点	标签	🔗	⭐
5	On the Emergence of Thinking in LLMs I: Searching for the Right Intuition	提出基于自博弈的强化学习（RLSP）框架，提升LLM的推理能力并涌现复杂行为。	reinforcement learning PPO