這些文章放到這裡我估計我也就不會讀了。主要是 google 瀏覽器的 bookmark 有點裝不下了，把它們清理一下。
移動端 agent
https://arxiv.org/pdf/2406.11896 DigiRL: Training In-The-Wild Device-Control
Agents with Autonomous Reinforcement Learning
agent 相關的環境
https://arxiv.org/pdf/2308.04026 An open-source sandbox for large language model evaluation
Reasoning？
https://arxiv.org/pdf/2212.10403 Towards Reasoning in Large Language Models: A Survey
Code generation
https://arxiv.org/pdf/2401.07339 CODEAGENT: Enhancing Code Generation with Tool-Integrated AgentSystems for Real-World Repo-level Coding Challenges
https://arxiv.org/pdf/2312.13010 AgentCoder: Multi-Agent Code Generation with
Effective Testing and Self-optimisation
https://arxiv.org/pdf/2405.17057 ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation 這篇我好還讀來著，但是它這個 reflection 是用來微調的，對當時寫 rubbish prompt 的我沒啥幫助？
未分類
Generative agents: Interactive simulacra of human behavior