[논문리뷰] ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative RankingarXiv에 게시된 'ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking' 논문에 대한 자세한 리뷰입니다.#Review#Reinforcement Learning#LLM Agents#Open-Ended Tasks#Relative Ranking#Tournament-based Ranking#Discriminative Collapse#Reward Modeling#Benchmarks2026년 1월 13일댓글 수 로딩 중