English
Related papers

Related papers: Combining On-Policy Optimization and Distillation …

200 papers

Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…

Computation and Language · Computer Science 2024-12-19 Tianyu Peng , Jiajun Zhang

Recent work has shown that augmenting environments with language descriptions improves policy learning. However, for environments with complex language abstractions, learning how to ground language to observations is difficult due to…

Machine Learning · Computer Science 2022-10-04 Victor Zhong , Jesse Mu , Luke Zettlemoyer , Edward Grefenstette , Tim Rocktäschel

Although pre-trained Vision-Language-Action (VLA) models exhibit impressive generalization in robotic manipulation, post-training remains crucial to ensure reliable performance during deployment. However, standard offline Supervised…

Robotics · Computer Science 2026-03-30 Zhide Zhong , Haodong Yan , Junfeng Li , Junjie He , Tianran Zhang , Haoang Li

On-policy distillation (OPD) is an increasingly important paradigm for post-training language models. However, we identify a pervasive Scaling Law of Miscalibration: while OPD effectively improves task accuracy, it systematically traps…

Machine Learning · Computer Science 2026-04-21 Jiaxin Zhang , Xiangyu Peng , Qinglin Chen , Qinyuan Ye , Caiming Xiong , Chien-Sheng Wu

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches.…

Machine Learning · Computer Science 2026-04-21 Yifeng Ding , Hung Le , Songyang Han , Kangrui Ruan , Zhenghui Jin , Varun Kumar , Zijian Wang , Anoop Deoras

Large Language Models (LLMs) demonstrate exceptional reasoning capabilities, often achieving state-of-the-art performance in various tasks. However, their substantial computational and memory demands, due to billions of parameters, hinder…

Computation and Language · Computer Science 2024-11-25 Xunyu Zhu , Jian Li , Can Ma , Weiping Wang

Reinforcement Learning has emerged as a dominant post-training approach to elicit agentic RAG behaviors such as search and planning from language models. Despite its success with larger models, applying RL to compact models (e.g., 0.5--1B…

Computation and Language · Computer Science 2026-04-28 Rikuto Kotoge , Mai Nishimura , Jiaxin Ma

The ability of large language models (LLMs) to process and reason over long textual inputs is critical for a wide range of real-world applications. However, progress in this area is significantly constrained by the absence of high-quality,…

Computation and Language · Computer Science 2025-09-05 Seganrasan Subramanian , Abhigya Verma

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) as it requires ensuring the correctness of each reasoning step. Researchers have been strengthening the mathematical reasoning abilities of LLMs…

Machine Learning · Computer Science 2025-06-23 Yunze Lin

Reinforcement learning is crucial for aligning large language models to perform complex reasoning tasks. However, current algorithms such as Group Relative Policy Optimization suffer from coarse grained, sequence level credit assignment,…

Machine Learning · Computer Science 2026-05-11 Hongbo Jin , Rongpeng Zhu , Zhongjing Du , Xu Jiang , Jingqi Tian , Qiaoman Zhang , Jiayu Ding

The exponential growth of Large Language Models (LLMs) continues to highlight the need for efficient strategies to meet ever-expanding computational and data demands. This survey provides a comprehensive analysis of two complementary…

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Artificial Intelligence · Computer Science 2025-11-14 Yuetai Li , Xiang Yue , Zhangchen Xu , Fengqing Jiang , Luyao Niu , Bill Yuchen Lin , Bhaskar Ramasubramanian , Radha Poovendran

In the field of large language models (LLMs), Knowledge Distillation (KD) is a critical technique for transferring capabilities from teacher models to student models. However, existing KD methods face limitations and challenges in…

Computation and Language · Computer Science 2025-04-08 Yixing Li , Yuxian Gu , Li Dong , Dequan Wang , Yu Cheng , Furu Wei

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement…

Computation and Language · Computer Science 2024-12-10 Junru Lu , Jiazheng Li , Siyu An , Meng Zhao , Yulan He , Di Yin , Xing Sun

On-policy reinforcement learning (RL) methods widely used for language model post-training, like Group Relative Policy Optimization (GRPO), often suffer from limited exploration and early saturation due to low sampling diversity. While…

Computation and Language · Computer Science 2026-01-30 Lei Yang , Wei Bi , Chenxi Sun , Renren Jin , Deyi Xiong

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

Offline reinforcement learning often requires a quality dataset that we can train a policy on. However, in many situations, it is not possible to get such a dataset, nor is it easy to train a policy to perform well in the actual environment…

Machine Learning · Computer Science 2025-11-04 Jonathan Light , Yuanzhe Liu , Ziniu Hu

Large language models have become increasingly popular and demonstrated remarkable performance in various natural language processing (NLP) tasks. However, these models are typically computationally expensive and difficult to be deployed in…

Computation and Language · Computer Science 2024-09-20 Dongheng Li , Yongchang Hao , Lili Mou

Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning,…

Artificial Intelligence · Computer Science 2026-05-29 Siyao Song , Cong Ma , Zhihao Cheng , Shiye Lei , Minghao Li , Ying Zeng , Huaixiao Tou , Kai Jia

Improving large language model (LLM) reasoning requires supervision that is both aligned with the model's own test-time states and informative at the token level. Reinforcement learning with verifiable rewards provides on-policy exploration…

Machine Learning · Computer Science 2026-04-30 Zhiquan Tan , Yinrong Hong