English
Related papers

Related papers: BroRL: Scaling Reinforcement Learning via Broadene…

200 papers

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly improved the performance of Large Language Models (LLMs) on tasks requiring multi-step reasoning. However, most RLVR pipelines rely on sparse outcome-based rewards,…

Computation and Language · Computer Science 2026-02-13 Runquan Gui , Yafu Li , Xiaoye Qu , Ziyan Liu , Yeqiu Cheng , Yu Cheng

When language models (LMs) are trained via reinforcement learning (RL) to generate natural language "reasoning chains", their performance improves on a variety of difficult question answering tasks. Today, almost all successful applications…

Machine Learning · Computer Science 2026-05-18 Mehul Damani , Isha Puri , Stewart Slocum , Idan Shenfeld , Leshem Choshen , Yoon Kim , Jacob Andreas

Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RL finetuning: some show substantial…

Machine Learning · Computer Science 2025-10-07 Zhepeng Cen , Yihang Yao , William Han , Zuxin Liu , Ding Zhao

Fine-tuning foundation models has emerged as a powerful approach for generating objects with specific desired properties. Reinforcement learning (RL) provides an effective framework for this purpose, enabling models to generate outputs that…

Machine Learning · Computer Science 2025-11-04 Pouya M. Ghari , Simone Sciabola , Ye Wang

Reinforcement learning with verifiable rewards (RLVR) has proven effective in training large reasoning models (LRMs) by leveraging answer-verifiable signals to guide policy optimization, which, however, suffers from high annotation costs.…

Machine Learning · Computer Science 2025-12-16 Shenzhi Yang , Guangcheng Zhu , Xing Zheng , Yingfan MA , Zhongqi Chen , Bowen Song , Weiqiang Wang , Junbo Zhao , Gang Chen , Haobo Wang

Recent advancements in Large Language Models have yielded significant improvements in complex reasoning tasks such as mathematics and programming. However, these models remain heavily dependent on annotated data and exhibit limited…

Machine Learning · Computer Science 2025-09-01 Jia Liu , ChangYi He , YingQiao Lin , MingMin Yang , FeiYang Shen , ShaoGuo Liu

As a paradigm for sequential decision making in unknown environments, reinforcement learning (RL) has received a flurry of attention in recent years. However, the explosion of model complexity in emerging applications and the presence of…

Machine Learning · Statistics 2025-07-22 Yuejie Chi , Yuxin Chen , Yuting Wei

Intrinsic rewards can improve exploration in reinforcement learning, but the exploration process may suffer from instability caused by non-stationary reward shaping and strong dependency on hyperparameters. In this work, we introduce…

Machine Learning · Computer Science 2022-02-10 Lukas Schäfer , Filippos Christianos , Josiah P. Hanna , Stefano V. Albrecht

Recent advances in Large Language Models(LLMs) have enabled strong performance in long-form writing, but current training paradigms remain limited: Supervised Fine-Tuning (SFT) remains constrained by data saturation and performance…

Computation and Language · Computer Science 2026-04-21 Xuanyu Lei , Chenliang Li , Yuning Wu , Kaiming Liu , Weizhou Shen , Peng Li , Ming Yan , Fei Huang , Ya-Qin Zhang , Yang Liu

Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but suffers from advantage collapse on ``hard samples'' where all rollouts fail. This lack of variance eliminates crucial learning signals.…

Machine Learning · Computer Science 2026-05-08 Xinyu Lu , Kaiqi Zhang , Jinglin Yang , Boxi Cao , Yaojie Lu , Hongyu Lin , Min He , Xianpei Han , Le Sun

Correctness-based Reinforcement Learning with Verifiable Rewards (RLVR) trains language models from binary feedback on sampled outputs, but the objective optimized in expectation and the stochastic update geometry induced by finite rollout…

Machine Learning · Computer Science 2026-05-29 Yifu Zheng

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Artificial Intelligence · Computer Science 2026-01-30 Zhao Wang , Ziliang Zhao , Zhicheng Dou

Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers from low success rates on difficult tasks and high costs of…

Machine Learning · Computer Science 2026-05-25 Weijie Shi , Yanxi Chen , Zexi Li , Xuchen Pan , Yuchang Sun , Jiajie Xu , Xiaofang Zhou , Yaliang Li

Efficiently acquiring external knowledge and up-to-date information is essential for effective reasoning and text generation in large language models (LLMs). Prompting advanced LLMs with reasoning capabilities to use search engines during…

Computation and Language · Computer Science 2025-08-07 Bowen Jin , Hansi Zeng , Zhenrui Yue , Jinsung Yoon , Sercan Arik , Dong Wang , Hamed Zamani , Jiawei Han

Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Reinforcement Learning with Verifiable Rewards (RLVR). While…

Artificial Intelligence · Computer Science 2026-04-21 Justin Bauer , Thomas Walshe , Derek Pham , Harit Vishwakarma , Armin Parchami , Frederic Sala , Paroma Varma

Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward often incentivizes models to be overconfident, leading to…

Machine Learning · Computer Science 2026-04-28 Liaoyaqi Wang , Chunsheng Zuo , William Jurayj , Benjamin Van Durme , Anqi Liu

Reinforcement Learning from Verifiable Rewards (RLVR) has improved language models in domains such as mathematics and code, where correctness can be checked automatically. However, many important tasks are only partially verifiable: prompts…

Computation and Language · Computer Science 2026-05-28 Saurabh Dash , Pierre Clavier , John Dang , Matthias Galle , Marzieh Fadaee , Ahmet Üstün , Beyza Ermis

Recent advancements in code generation have shown remarkable success across software domains, yet hardware description languages (HDLs) such as Verilog remain underexplored due to their concurrency semantics, syntactic rigidity, and…

Machine Learning · Computer Science 2025-08-27 Fu Teng , Miao Pan , Xuhong Zhang , Zhezhi He , Yiyao Yang , Xinyi Chai , Mengnan Qi , Liqiang Lu , Jianwei Yin

Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For…

Artificial Intelligence · Computer Science 2025-10-30 Tianqianjin Lin , Xi Zhao , Xingyao Zhang , Rujiao Long , Yi Xu , Zhuoren Jiang , Wenbo Su , Bo Zheng

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…

‹ Prev 1 8 9 10 Next ›