The paper introduces MoEvolve, a bidirectional distillation framework that leverages increased activation budgets in Mixture-of-Experts (MoE) models to create a stronger internal teacher. By first restoring a high‑k model and then transferring its enhanced capabilities back to the original low‑k configuration, MoEvolve improves performance across various MoE models and benchmarks, achieving up to 22.2 domain‑average points and outperforming same‑budget RLVR baselines by up to 6.5 points. The resulting low‑k models often surpass their activation‑expanded teachers.
By Haoyu Chen, Jun Bai, Yang Liu, Jianfei Zhang, Wenge Rong
The paper investigates three fusion paradigms—Merge, Mix RL, and multi‑teacher on‑policy distillation (MOPD)—for consolidating reinforcement learning with verifiable rewards (RLVR) across multiple domains. Experiments across model scales and a multi‑domain benchmark show that while overall performance differences are small, significant gaps can appear on specific tasks, and each method exhibits distinct training dynamics and constraints. Practical guidelines are offered: Merge for cheap fusion when experts exist, Mix RL for unified training with adjustable domain mixtures, and MOPD when preserving domain‑specific gains is paramount.
By Siye Wu, Kai Yang, Yuchen Cai, Xin Xu, Peng-Yuan Wang, Jiaxuan Wang, Jiashun Liu, Jiafei Lyu, Yangkun Chen, Saiyong Yang, Yanghua Xiao
PIVOT introduces a dynamic transition framework for vertical-domain few-shot distillation, routing samples between On-Policy Distillation (OPD) and GRPO-based reinforcement learning based on teacher-evaluated perplexity. Low-perplexity samples are moved to GRPO for reward-driven refinement, while high-perplexity samples remain under OPD to continue acquiring domain knowledge. Experiments on Banking77 and HWU64 demonstrate that PIVOT outperforms both continued OPD and globally synchronized OPD→GRPO baselines, achieving stronger downstream performance and more stable training dynamics.
By Heng Li, Yong Zhang, Ning Cheng, Zhigen Li, Yun Zhu, Yanmeng Wang, Shaojun Wang, Jing Xiao
arXiv:2606. 30406v1 Announce Type: cross Abstract: Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabilities into one model remains hard.
By Wenhan Ma, Jianyu Wei, Liang Zhao, Hailin Zhang, Bangjun Xiao, Lei Li, Qibin Yang, Bofei Gao, Yudong Wang, Rang Li, Jinhao Dong, Zhifang Sui, Fuli Luo
The paper introduces Joint On-Policy Learning and Teaching (JOLT), a method that trains a single policy to act both as a privileged teacher and an unprivileged student. It derives a condition ensuring the teacher’s distillation update aligns positively with the student’s reward gradient, leading to a KL‑regularized teacher objective that matches the student’s current capabilities. Experiments show JOLT improves training efficiency and performance across various tasks, with additional gains when student rewards are incorporated.
By Randy Ardywibowo, Arnav Dalal, Jiantao Jiao
The paper introduces Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation (Road MOPD), a method that adds non-routed teachers as auxiliary cross-domain critics to address gradient conflicts in multi-teacher distillation. It employs token-level credit assignment based on teacher agreement and preventive gradient projection to coordinate updates and reduce conflicts. Experiments show that Road MOPD improves performance, especially in high-conflict scenarios, and mitigates degradation in disadvantaged domains.
By Shi-Yu Tian, Yong Liu, Ximan Liu, Tianrui Zhu, Sule Bai, Xinwei Yang, Ruiqi Liu, Kun-Yang Yu, Ming Yang, Zhi Zhou, Yu-Feng Li, Yipeng Sun, Gu Simiu
arXiv:2605. 03677v2 Announce Type: replace Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models into a single student model.
By Wenjin Hou, Shangpin Peng, Weinong Wang, Zheng Ruan, Yue Zhang, Zhenglin Zhou, Mingqi Gao, Yifei Chen, Kaiqi Wang, Hongming Yang, Chengquan Zhang, Zhuotao Tian, Han Hu, Yi Yang, Fei Wu, Hehe Fan
arXiv:2609.32493v2 Announce Type: replace-cross
Abstract: Distillation enables student language models to acquire new capabilities from expert teachers. However, integrating knowledge from multi-teac...
By Huihao Jing, Wenbin Hu, Shaojin Chen, Haochen Shi, Zhongwei Xie, Guijia Zhang, Yuxuan Liu, Haoyu Huang, Haoran Li, Yangqiu Song
arXiv:2609.34658v2 Announce Type: replace
Abstract: Reward-specialized post-training produces strong experts for flow-based generative models, while multi-teacher on-policy distillation (OPD) consoli...
By Pengyang Ling, Jiazi Bu, Yujie Zhou, Yibin Wang, Zeqiang Lai, Xiaoxiao Ma, Yi Jin, Huaian Chen, Yuhang Zang
arXiv:2606. 00609v1 Announce Type: cross Abstract: Reinforcement learning (RL) with verifiable rewards has achieved strong progress in reasoning-oriented LLMs, but extending it to multi-domain RL remains challenging due to reward unreliability in non-verifiable tasks and capability interference across domains.
By Rui Zhang, Xinle Wu, Yao Lu
arXiv:2610. 13205v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a target policy on its own rollouts using token-level supervision from a stronger teacher, but typically relies on the teacher being substantially more capable than the target.
By Rong Wu, Daocheng Fu, Yu Yang, Xuemeng Yang, Siqi Li, Shu Zou, Yao Zhu, Botian Shi, Bo Zhang, Cong Zhang, Pinlong Cai, Jianbiao Mei
Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck.