English
Related papers

Related papers: Reinforcement Learning via Self-Distillation

200 papers

Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-teacher. Unlike GRPO,…

Machine Learning · Computer Science 2026-05-28 Zehao Liu , Yuanpu Cao , Jinghui Chen , Vasant G. Honavar

Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing…

Machine Learning · Computer Science 2026-05-20 Yang Li , Erik Nijkamp , Semih Yavuz , Shafiq Joty

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignment uniformly…

Machine Learning · Computer Science 2026-04-03 Gengsheng Li , Tianyu Yang , Junfeng Fang , Mingyang Song , Mao Zheng , Haiyun Guo , Dan Zhang , Jinqiao Wang , Tat-Seng Chua

Direct Preference Optimization (DPO) is a powerful paradigm to align language models with human preferences using pairwise comparisons. However, its binary win-or-loss supervision often proves insufficient for training small models with…

Computation and Language · Computer Science 2025-09-23 Minchan Kwon , Junwon Ko , Kangil Kim , Junmo Kim

Current post-training methods in verifiable settings fall into two categories. Reinforcement learning (RLVR) relies on binary rewards, which are broadly applicable and powerful, but provide only sparse supervision during training.…

Computation and Language · Computer Science 2026-04-15 Yinghui He , Simran Kaur , Adithya Bhaskar , Yongjin Yang , Jiarui Liu , Narutatsu Ri , Liam Fowl , Abhishek Panigrahi , Danqi Chen , Sanjeev Arora

Large language models trained with reinforcement learning (RL) for mathematical reasoning face a fundamental challenge: on problems the model cannot solve at all - "cliff" prompts - the RL gradient vanishes entirely, preventing any learning…

Machine Learning · Computer Science 2026-03-26 Ken Ding

When a model produces a correct solution under reinforcement learning with verifiable rewards (RLVR), every token receives the same reward signal regardless of whether it was a decisive reasoning step or a grammatical filler. A natural fix…

Machine Learning · Computer Science 2026-05-20 Ahmed Heakl , Abdelrahman M. Shaker , Youssef Mohamed , Rania Elbadry , Omar Fetouh , Fahad Shahbaz Khan , Salman Khan

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Enabling Large Language Models (LLMs) to continuously improve from environmental interactions is a central challenge in post-training. While on-policy self-distillation offers a promising paradigm, existing methods predominantly treat…

Machine Learning · Computer Science 2026-05-14 Yuwei Zhang , Sha Li , Changlong Yu , Qin Lu , Shuowei Jin , Chengyu Dong , Haoran Liu , Ilgee Hong , Xintong Li , Zhenyu Shi , Bing Yin , Jingbo Shang

Reinforcement learning (RL) has emerged as a promising paradigm for inducing explicit reasoning behaviors in large language and vision-language models. However, reasoning-oriented RL post-training remains fundamentally challenging due to…

Artificial Intelligence · Computer Science 2026-05-13 Fan Yang , Rui Meng , Trudi Di Qi , Ali Ezzati , Yuxin Wen

Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-policy reinforcement learning can reduce forgetting, it…

Machine Learning · Computer Science 2026-01-28 Idan Shenfeld , Mehul Damani , Jonas Hübotter , Pulkit Agrawal

On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to provide dense, fine-grained signals for each sampled trajectory, in contrast to reinforcement…

Machine Learning · Computer Science 2026-04-09 Chenxu Yang , Chuanyu Qin , Qingyi Si , Minghui Chen , Naibin Gu , Dingyu Yao , Zheng Lin , Weiping Wang , Jiaqi Wang , Nan Duan

The success of RL for LLM post-training stems from an unreasonably uninformative source: a single bit of information per rollout as binary reward or preference label. At the other extreme, distillation offers dense supervision but requires…

Machine Learning · Computer Science 2026-02-12 Yuda Song , Lili Chen , Fahim Tajwar , Remi Munos , Deepak Pathak , J. Andrew Bagnell , Aarti Singh , Andrea Zanette

Search-augmented reasoning agents interleave internal reasoning with calls to an external retriever, and their performance relies on the quality of each issued query. However, under outcome-reward reinforcement learning, every search…

Artificial Intelligence · Computer Science 2026-05-19 Yufei Ma , Zihan Liang , Ben Chen , Zhipeng Qian , Huangyu Dai , Lingtao Mao , Xuxin Zhang , Chenyi Lei , Wenwu Ou

Recent advances in large reasoning models have leveraged reinforcement learning with verifiable rewards (RLVR) to improve reasoning capabilities. However, scaling these methods typically requires extensive rollout computation and large…

Machine Learning · Computer Science 2025-09-03 Xinyu Tang , Zhenduo Zhang , Yurou Liu , Wayne Xin Zhao , Zujie Wen , Zhiqiang Zhang , Jun Zhou

Reinforcement learning with verifiable rewards has emerged as a promising paradigm for enhancing the reasoning capabilities of large language models particularly in mathematics. Current approaches in this domain present a clear trade-off:…

Computation and Language · Computer Science 2026-02-03 Batuhan K. Karaman , Aditya Rawal , Suhaila Shakiah , Mohammad Ghavamzadeh , Mingyi Hong , Arijit Biswas , Ruida Zhou

Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of methods replaces…

Machine Learning · Computer Science 2026-05-29 Xiaohang Tang , Keyue Jiang , Che Liu , Qifang Zhao , Xiaoxiao Xu , Sangwoong Yoon , Ilija Bogunovic

Moving beyond simple scalar rewards toward richer world feedback is a natural path to more scalable RL post-training. On-policy self-distillation (OPSD) is a promising recent approach that uses arbitrary feedback as learning signal, yet its…

Machine Learning · Computer Science 2026-05-29 Tommy He , Jerome Sieber , Matteo Saponati

With growing interest in deploying text-to-video (T2V) models in resource-constrained environments, reducing their high computational cost has become crucial, leading to extensive research on pruning and knowledge distillation methods while…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Jisoo Kim , Wooseok Seo , Junwan Kim , Seungho Park , Sooyeon Park , Youngjae Yu

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…

Computation and Language · Computer Science 2026-05-14 Leyi Pan , Shuchang Tao , Yunpeng Zhai , Zheyu Fu , Liancheng Fang , Minghua He , Lingzhe Zhang , Zhaoyang Liu , Bolin Ding , Aiwei Liu , Lijie Wen
‹ Prev 1 2 3 10 Next ›