Instead of comparing each generated response only against a group average, LambdaPO learns from fine-grained pairwise reward differences among sampled reasoning trajectories. This helps the model better distinguish high-quality reasoning paths, improve credit assignment, and reduce unstable optimization behavior during RL training.
1@article{yuan2026lambdapo,
2 title={LambdaPO: A Lambda Style Policy Optimization for Reasoning Language Models},
3 author={Yuan, Zhe and Zhou, Yipeng and Li, Jinghan and Chen, Xinyuan and Deng, Bowen and Chen, Zhiqian and Zhao, Liang},
4 year={2026}
5}
