[논문리뷰] SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative TasksarXiv에 게시된 'SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks' 논문에 대한 자세한 리뷰입니다.#Review#SlopCodeBench#Coding Agents#Iterative Development#Code Quality#Structural Erosion#Verbosity#Benchmarking#Long-Horizon Tasks2026년 3월 26일댓글 수 로딩 중
[논문리뷰] CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in ProductionarXiv에 게시된 'CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production' 논문에 대한 자세한 리뷰입니다.#Review#LLM#Social Chat#Engagement Optimization#Steerability#Reinforcement Learning#Reward Modeling#A/B Testing#Iterative Development2026년 3월 2일댓글 수 로딩 중