English
Related papers

Related papers: STRIDE: Learnable Stepwise Language Feedback for L…

200 papers

Despite achieving remarkable success in complex tasks, Deep Reinforcement Learning (DRL) is still suffering from critical issues in practical applications, such as low data efficiency, lack of interpretability, and limited cross-environment…

Artificial Intelligence · Computer Science 2026-03-10 Chang Yao , Jinghui Qin , Kebing Jin , Hankz Hankui Zhuo

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across…

Machine Learning · Computer Science 2026-05-26 Fei Ding , Yongkang Zhang , youwei wang , Zijian Zeng

Large Language Models (LLMs) have demonstrated remarkable creative writing capabilities, yet their substantial computational demands hinder widespread use. Enhancing Small Language Models (SLMs) offers a promising alternative, but current…

Computation and Language · Computer Science 2025-09-01 Xiaolong Wei , Bo Lu , Xingyu Zhang , Zhejun Zhao , Dongdong Shen , Long Xia , Dawei Yin

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

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning trajectories as pseudo-gradient descent updates to the LLM's…

Computation and Language · Computer Science 2025-05-27 Junnan Liu , Hongwei Liu , Linchen Xiao , Shudong Liu , Taolin Zhang , Zihan Ma , Songyang Zhang , Kai Chen

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same…

Machine Learning · Computer Science 2025-04-29 Zhaoyang Wang , Weilei He , Zhiyuan Liang , Xuchao Zhang , Chetan Bansal , Ying Wei , Weitong Zhang , Huaxiu Yao

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…

Computation and Language · Computer Science 2026-05-19 Zhichao Wang , Kiran Ramnath , Bin Bi , Shiva Kumar Pentyala , Sougata Chaudhuri , Shubham Mehrotra , Zixu , Zhu , Xiang-Bo Mao , Sitaram Asur , Na , Cheng

Logical reasoning is a pivotal component in the field of artificial intelligence. Proof planning, particularly in contexts requiring the validation of explanation accuracy, continues to present challenges. The recent advancement of large…

Computation and Language · Computer Science 2025-10-31 Ying Su , Mingwen Liu , Zhijiang Guo

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

Cryptography and Security · Computer Science 2026-05-21 Junxi Chen , Junhao Dong , Xiaohua Xie

Large language models (LLMs) can improve their accuracy on various tasks through iteratively refining and revising their output based on feedback. We observe that these revisions can introduce errors, in which case it is better to roll back…

Artificial Intelligence · Computer Science 2023-09-26 Kumar Shridhar , Harsh Jhamtani , Hao Fang , Benjamin Van Durme , Jason Eisner , Patrick Xia

Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful…

Artificial Intelligence · Computer Science 2026-05-08 Tianyang Han , Hengyu Shi , Junjie Hu , Xu Yang , Zhiling Wang , Junhao Su

Large language models (LLMs) have significantly improved their reasoning capabilities; however, they still struggle with complex multi-step mathematical problem-solving due to error propagation, lack of self-correction, and limited…

Machine Learning · Computer Science 2025-03-10 Joykirat Singh , Tanmoy Chakraborty , Akshay Nambi

In the context of multi-step reasoning, e.g., with chain-of-thought, language models (LMs) can easily assign a high likelihood to incorrect steps. As a result, decoding strategies that optimize for solution likelihood often yield incorrect…

Computation and Language · Computer Science 2026-01-06 Muhammad Khalifa , Lajanugen Logeswaran , Moontae Lee , Honglak Lee , Lu Wang

Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. In practice, RL progress often…

Artificial Intelligence · Computer Science 2026-05-05 Caijun Xu , Changyi Xiao , Zhongyuan Peng , Xinrun Wang , Yixin Cao

Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs. However, existing methods suffer from a critical issue we term Semantic…

Information Retrieval · Computer Science 2026-01-09 Chengcheng Guo , Kuo Cai , Yu Zhou , Qiang Luo , Ruiming Tang , Han Li , Kun Gai , Guorui Zhou

Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and reasoning capabilities in favor of static embeddings. We…

Computation and Language · Computer Science 2025-10-07 Jiashuo Sun , Shixuan Liu , Zhaochen Su , Xianrui Zhong , Pengcheng Jiang , Bowen Jin , Peiran Li , Weijia Shi , Jiawei Han

Recent advances in reinforcement learning (RL) using numerical rewards have significantly enhanced the complex reasoning capabilities of large language models (LLMs). However, we identify three fundamental limitations of purely numerical…

Computation and Language · Computer Science 2026-02-23 Xiaoying Zhang , Yipeng Zhang , Hao Sun , Kaituo Feng , Chaochao Lu , Chao Yang , Helen Meng

Reinforcement Learning with Verifiable Rewards (RLVR), particularly with algorithms like Group Relative Policy Optimization (GRPO), has proven highly effective in enhancing the reasoning capabilities of large language models. However, a…

Computation and Language · Computer Science 2026-03-03 Shangyu Xing , Siyuan Wang , Chenyuan Yang , Xinyu Dai , Xiang Ren

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

Machine Learning · Computer Science 2025-10-21 Guofu Xie , Yunsheng Shi , Hongtao Tian , Ting Yao , Xiao Zhang