https://aclanthology.org/2025.coling-main.504/ DORA: Dynamic Optimization Prompt for Continuous Reflection of LLM-based AgentKun Li, Tingzhang Zhao, Wei Zhou, Songlin Hu. Proceedings of the 31st International Conference on Computational Linguistics. 2025.aclanthology.org 기존 Reflcetion은 성능을 올리긴 했지만 iteration이 증가할 수록 성능 향상이 더뎌졌다.위 그래프에서 보듯 Early Stop Reflection문제가 발생하였고, DORA(Dynamic and Optimized..