English
Related papers

Related papers: DLER: Doing Length pEnalty Right - Incentivizing M…

200 papers

Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks…

Artificial Intelligence · Computer Science 2025-09-09 Haoyang He , Zihua Rong , Kun Ji , Chenyang Li , Qing Huang , Chong Xia , Lan Yang , Honggang Zhang

Reinforcement learning substantially improves reasoning in large language models, but it also tends to lengthen chain of thought outputs and increase computational cost during both training and inference. Though length control methods have…

Computation and Language · Computer Science 2026-02-12 Daisuke Nohara , Taishi Nakamura , Rio Yokota

Reinforcement learning (RL) is attracting attention as an effective way to solve sequential optimization problems that involve high dimensional state/action space and stochastic uncertainties. Many such problems involve constraints…

Machine Learning · Computer Science 2021-04-01 Haeun Yoo , Victor M. Zavala , Jay H. Lee

Large reasoning models (LRMs) achieve higher performance on challenging reasoning tasks by generating more tokens at inference time, but this verbosity often wastes computation on easy problems. Existing solutions, including supervised…

Artificial Intelligence · Computer Science 2025-06-09 Violet Xiang , Chase Blagden , Rafael Rafailov , Nathan Lile , Sang Truong , Chelsea Finn , Nick Haber

Video reasoning has advanced with large multimodal models (LMMs), yet their inference is often a single pass that returns an answer without verifying whether the reasoning is evidence-aligned. We introduce Reinforce to Learn, Elect to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Songyuan Yang , Weijiang Yu , Jilin Ma , Ziyu Liu , Guijian Tang , Wenjing Yang , Huibin Tan , Nong Xiao

Large reasoning models, such as OpenAI o1 or DeepSeek R1, have demonstrated remarkable performance on reasoning tasks but often incur a long reasoning path with significant memory and time costs. Existing methods primarily aim to shorten…

Artificial Intelligence · Computer Science 2026-03-17 Danlong Yuan , Tian Xie , Shaohan Huang , Zhuocheng Gong , Huishuai Zhang , Chong Luo , Furu Wei , Dongyan Zhao

Large language models (LLMs) have demonstrated significant advancements in reasoning capabilities, performing well on various challenging benchmarks. Techniques like Chain-of-Thought prompting have been introduced to further improve…

Computation and Language · Computer Science 2025-06-13 Zehui Ling , Deshu Chen , Hongwei Zhang , Yifeng Jiao , Xin Guo , Yuan Cheng

Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Although reinforcement learning (RL) has been used to improve reasoning, most methods focus on accuracy…

Machine Learning · Computer Science 2026-04-20 Hanbing Liu , Lang Cao , Yuanyi Ren , Mengyu Zhou , Haoyu Dong , Xiaojun Ma , Shi Han , Dongmei Zhang

Recent studies show that the reasoning capabilities of Large Language Models (LLMs) can be improved by applying Reinforcement Learning (RL) to question-answering (QA) tasks in areas such as math and coding. With a long context length, LLMs…

Computation and Language · Computer Science 2025-10-17 Stephen Chung , Wenyu Du , Jie Fu

Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a…

Computation and Language · Computer Science 2025-08-11 Ruosen Li , Ziming Luo , Quan Zhang , Ruochen Li , Ben Zhou , Ali Payani , Xinya Du

Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as "overthinking." Existing solutions via reinforcement learning (RL) typically penalize generated tokens to…

Computation and Language · Computer Science 2025-12-02 Canhui Wu , Qiong Cao , Chang Li , Zhenfang Wang , Chao Xue , Yuwei Fan , Wei Xi , Xiaodong He

Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs), enabling the development of large reasoning models (LRMs). However, LRMs such as DeepSeek-R1 and…

Artificial Intelligence · Computer Science 2025-11-13 Yuhao Wang , Xiaopeng Li , Cheng Gong , Ziru Liu , Suiyun Zhang , Rui Liu , Xiangyu Zhao

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require,…

Machine Learning · Computer Science 2026-05-12 Songtao Wei , Yi Li , Zhikai Li , Xu Hu , Yuede Ji , Guanpeng Li , Feng Chen , Carl Yang , Zhichun Guo , Bingzhe Li

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Computation and Language · Computer Science 2025-05-27 Jinyan Su , Claire Cardie

Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems we often want to reach the goal quickly, and LRM reasoning can be viewed…

Machine Learning · Computer Science 2026-05-27 Alex Ayoub , Kavosh Asadi , Dale Schuurmans , Csaba Szepesvári , Karim Bouyarmane

Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL), particularly by generating long reasoning traces. However, these extended outputs often exhibit substantial…

Computation and Language · Computer Science 2025-05-22 Wei Liu , Ruochen Zhou , Yiyun Deng , Yuzhen Huang , Junteng Liu , Yuntian Deng , Yizhe Zhang , Junxian He

Existing approaches typically rely on fixed length penalties, but such penalties are hard to tune and fail to adapt to the evolving reasoning abilities of LLMs, leading to suboptimal trade-offs between accuracy and conciseness. To address…

Artificial Intelligence · Computer Science 2025-12-29 Yanhao Li , Lu Ma , Jiaran Zhang , Lexiang Tang , Wentao Zhang , Guibo Luo

Reinforcement Learning with Verifiable Rewards (RLVR) can elicit strong multi-step reasoning, yet it often encourages overly verbose traces. Moreover, naive length penalties in group-relative optimization can severely hurt accuracy. We…

Computation and Language · Computer Science 2026-02-03 Keqin Peng , Yuanxin Ouyang , Xuebo Liu , Zhiliang Tian , Ruijian Han , Yancheng Yuan , Liang Ding

Reinforcement Learning has emerged as a key driver for LLM reasoning. This capability is equally pivotal in long-context scenarios--such as long-dialogue understanding and structured data analysis, where the challenge extends beyond…

Computation and Language · Computer Science 2026-02-06 Bowen Ping , Zijun Chen , Yiyao Yu , Tingfeng Hui , Junchi Yan , Baobao Chang

Large reasoning models enhanced by reinforcement learning with verifiable rewards have achieved significant performance gains by extending their chain-of-thought. However, this paradigm incurs substantial deployment costs as models often…

Artificial Intelligence · Computer Science 2026-05-15 Wei Wu , Liyi Chen , Congxi Xiao , Tianfu Wang , Qimeng Wang , Chengqiang Lu , Yan Gao , Yi Wu , Yao Hu , Hui Xiong
‹ Prev 1 2 3 10 Next ›