@article{readthetracesteerthepathtrajectoryawarer, title = {Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models}, author = {Anant Khandelwal and Manish Gupta}, year = {2026}, eprint = {2606.04396}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.04396}, }