@article{pairprefixawareinternalrewardmodelformul, title = {PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization}, author = {Wonjoong Kim and Yeonjun In and Sangwu Park and Dongha Lee and Chanyoung Park}, year = {2026}, eprint = {2605.17877}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.17877}, }