English
Related papers

Related papers: Implicit Compression Regularization: Concise Reaso…

200 papers

We propose Re-FORC, an adaptive reward prediction method that, given a context, enables prediction of the expected future rewards as a function of the number of future thinking tokens. Re-FORC trains a lightweight adapter on reasoning…

Artificial Intelligence · Computer Science 2025-11-05 Renos Zabounidis , Aditya Golatkar , Michael Kleinman , Alessandro Achille , Wei Xia , Stefano Soatto

Recent advancements have endowed Large Language Models (LLMs) with impressive general reasoning capabilities, yet they often struggle with personalization reasoning - the crucial ability to analyze user history, infer unique preferences,…

Computation and Language · Computer Science 2025-09-30 Song Jin , Juntian Zhang , Yong Liu , Xun Zhang , Yufei Zhang , Fei Jiang , Guojun Yin , Wei Lin , Rui Yan

Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain…

Computation and Language · Computer Science 2026-02-24 Yinuo Xu , Shuo Lu , Jianjie Cheng , Meng Wang , Qianlong Xie , Xingxing Wang , Ran He , Jian Liang

Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete token sequences. This creates a mismatch between the optimization space and the structure of…

Machine Learning · Computer Science 2026-05-19 Haoqiang Kang , Yizhe Zhang , Nikki Lijing Kuang , Yi-An Ma , Lianhui Qin

Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce substantial computational overhead and latency,…

Computation and Language · Computer Science 2025-10-10 Songjun Tu , Jiahao Lin , Qichao Zhang , Xiangyu Tian , Linjing Li , Xiangyuan Lan , Dongbin Zhao

Chain-of-thought (CoT) reasoning has enabled large language models (LLMs) to utilize additional computation through intermediate tokens to solve complex tasks. However, we posit that typical reasoning traces contain many redundant tokens,…

Computation and Language · Computer Science 2025-06-11 Tergel Munkhbat , Namgyu Ho , Seo Hyun Kim , Yongjin Yang , Yujin Kim , Se-Young Yun

While reasoning large language models (LLMs) demonstrate remarkable performance across various tasks, they also contain notable security vulnerabilities. Recent research has uncovered a "thinking-stopped" vulnerability in DeepSeek-R1, where…

Cryptography and Security · Computer Science 2025-04-30 Yu Cui , Yujun Cai , Yiwei Wang

Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but runs the risk of producing post-hoc rationalizations: when models can see the answer during generation, the answer serves as a cognitive…

Computation and Language · Computer Science 2026-02-17 Guangyue Peng , Zongchao Chen , Wen Luo , Yuntao Wen , Wei Li , Ruixiang Feng , Ran Le , Chen Yang , Zhenwei An , Yang Song , Tao Zhang , Houfeng Wang

As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing accordingly. We argue that a thorough understanding of the instruction itself,…

Computation and Language · Computer Science 2026-04-21 Yuancheng Yang , Lin Yang , Xu Wang , Chao Tong , Haihua Yang

Reinforcement learning (RL) has become a key approach for enhancing reasoning in large language models (LLMs), yet scalable training is often hindered by the rapid collapse of policy entropy, which leads to premature convergence and…

Machine Learning · Computer Science 2026-04-14 Ming Lei , Christophe Baehr

Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by enabling step-by-step problem-solving, yet its extension to Long-CoT introduces substantial computational overhead due to increased token length. Existing compression…

Computation and Language · Computer Science 2025-11-14 Yibo Wang , Haotian Luo , Huanjin Yao , Tiansheng Huang , Haiying He , Rui Liu , Naiqiang Tan , Jiaxing Huang , Xiaochun Cao , Dacheng Tao , Li Shen

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

We find that the response length of reasoning LLMs, whether trained by reinforcement learning or supervised learning, drastically increases for ill-posed questions with missing premises (MiP), ending up with redundant and ineffective…

Artificial Intelligence · Computer Science 2025-04-14 Chenrui Fan , Ming Li , Lichao Sun , Tianyi Zhou

Inverse Reinforcement Learning (IRL) is a powerful set of techniques for imitation learning that aims to learn a reward function that rationalizes expert demonstrations. Unfortunately, traditional IRL methods suffer from a computational…

Machine Learning · Computer Science 2024-01-31 Gokul Swamy , Sanjiban Choudhury , J. Andrew Bagnell , Zhiwei Steven Wu

Recent advances in test-time scaling suggest that Large Language Models (LLMs) can gain better capabilities by generating Chain-of-Thought reasoning (analogous to human thinking) to respond a given request, and meanwhile exploring more…

Machine Learning · Computer Science 2025-05-20 Yuhang Wang , Youhe Jiang , Bin Cui , Fangcheng Fu

Reinforcement learning with verifiable rewards (RLVR) recently thrives in large language model (LLM) reasoning tasks. However, the reward sparsity and the long reasoning horizon make effective exploration challenging. In practice, this…

Artificial Intelligence · Computer Science 2026-05-12 Yifan Xu , Junren Chen , Yifan Chen

Recent generations of language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their…

Artificial Intelligence · Computer Science 2025-11-21 Parshin Shojaee , Iman Mirzadeh , Keivan Alizadeh , Maxwell Horton , Samy Bengio , Mehrdad Farajtabar

Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate…

Machine Learning · Computer Science 2023-03-10 Shaohui Peng , Xing Hu , Rui Zhang , Jiaming Guo , Qi Yi , Ruizhi Chen , Zidong Du , Ling Li , Qi Guo , Yunji Chen

Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (ICL). Although these two modes offer complementary…

Machine Learning · Computer Science 2026-04-03 Arslan Chaudhry , Sridhar Thiagarajan , Andrew Lampinen

Simplicity is a powerful inductive bias. In reinforcement learning, regularization is used for simpler policies, data augmentation for simpler representations, and sparse reward functions for simpler objectives, all that, with the…

Machine Learning · Computer Science 2025-05-23 Bang You , Puze Liu , Huaping Liu , Jan Peters , Oleg Arenz