English
Related papers

Related papers: Learning from Self-Debate: Preparing Reasoning Mod…

200 papers

Our work aims at efficiently leveraging ambiguous demonstrations for the training of a reinforcement learning (RL) agent. An ambiguous demonstration can usually be interpreted in multiple ways, which severely hinders the RL-Agent from…

Machine Learning · Computer Science 2024-02-09 Yantian Zha , Lin Guan , Subbarao Kambhampati

Leveraging more test-time computation has proven to be an effective way to boost the reasoning capabilities of large language models (LLMs). Among various methods, the verify-and-improve paradigm stands out for enabling dynamic solution…

Machine Learning · Computer Science 2025-06-11 Yurun Yuan , Tengyang Xie

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced reasoning capabilities in Large Language Models. However, adapting RLVR to multimodal domains suffers from a critical \textit{perception-reasoning decoupling}.…

Artificial Intelligence · Computer Science 2026-01-13 Shujian Gao , Yuan Wang , Jiangtao Yan , Zuxuan Wu , Yu-Gang Jiang

The development of reasoning capabilities represents a critical frontier in large language models (LLMs) research, where reinforcement learning (RL) and process reward models (PRMs) have emerged as predominant methodological frameworks.…

Artificial Intelligence · Computer Science 2025-12-09 Zhangying Feng , Qianglong Chen , Ning Lu , Yongqian Li , Siqi Cheng , Shuangmu Peng , Duyu Tang , Shengcai Liu , Zhirui Zhang

Large Language Models (LLMs) have demonstrated significant capabilities in understanding and generating human language, contributing to more natural interactions with complex systems. However, they face challenges such as ambiguity in user…

Computation and Language · Computer Science 2025-07-17 Ana Davila , Jacinto Colan , Yasuhisa Hasegawa

Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the…

Computation and Language · Computer Science 2025-07-30 Carel van Niekerk , Renato Vukovic , Benjamin Matthias Ruppik , Hsien-chin Lin , Milica Gašić

Large language models (LLMs) often struggle to learn from corrective feedback within a conversational context. They are rarely proactive in soliciting this feedback, even when faced with ambiguity, which can make their dialogues feel…

Computation and Language · Computer Science 2026-02-19 Jonathan Cook , Diego Antognini , Martin Klissarov , Claudiu Musat , Edward Grefenstette

Reinforcement learning (RL) has proven highly effective in eliciting the reasoning capabilities of large language models (LLMs). Inspired by this success, recent studies have explored applying similar techniques to vision-language models…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Yan Chen , Long Li , Teng Xi , Long Zeng , Jingdong Wang

Despite recent advances in the reasoning capabilities of Large Language Models (LLMs), improving the reasoning ability of Small Language Models (SLMs, e.g., up to 1.5B parameters) remains challenging. A key obstacle lies in the complexity…

Computation and Language · Computer Science 2025-12-16 Li Wang , Changhao Zhang , Zengqi Xiu , Kai Lu , Xin Yu , Kui Zhang , Wenjun Wu

Large language models (LLMs) have exhibited remarkable performance on complex reasoning tasks, with reinforcement learning under verifiable rewards (RLVR) emerging as a principled framework for aligning model behavior with reasoning chains.…

Artificial Intelligence · Computer Science 2026-05-05 Yunjian Zhang , Sudong Wang , Yang Li , Peiran Xu , Conghao Zhou , Xiaoyue Ma , Jianing Li , Yao Zhu

Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this work, we demonstrate that, surprisingly, RL emerges during the inference time of large language models (LLMs), a phenomenon we term…

Machine Learning · Computer Science 2026-04-28 Kefan Song , Amir Moeini , Peng Wang , Lei Gong , Rohan Chandra , Shangtong Zhang , Yanjun Qi

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However,…

Computation and Language · Computer Science 2026-04-10 Panatchakorn Anantaprayoon , Nataliia Babina , Nima Asgharbeygi , Jad Tarifi

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning performance of large language models (LLMs) by increasing test-time compute. However, even after extensive RLVR training, such models still…

Artificial Intelligence · Computer Science 2026-03-10 Pinzheng Wang , Shuli Xu , Juntao Li , Yu Luo , Dong Li , Jianye Hao , Min 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

Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for training LLM agents. However, RLVR highly depends on well-crafted task queries and corresponding ground-truth answers to provide accurate rewards,…

Machine Learning · Computer Science 2026-05-20 Hongliang Lu , Yuhang Wen , Pengyu Cheng , Ruijin Ding , Jiaqi Guo , Haotian Xu , Chutian Wang , Haonan Chen , Xiaoxi Jiang , Guanjun Jiang

Large language models (LLMs) have demonstrated outstanding performance across various tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic content. One potential approach to mitigate these issues…

Computation and Language · Computer Science 2024-07-19 Yuxuan Yao , Han Wu , Zhijiang Guo , Biyan Zhou , Jiahui Gao , Sichun Luo , Hanxu Hou , Xiaojin Fu , Linqi Song

Large language model (LLM)--based agents have emerged as pivotal tools in assisting human experts across various fields by transforming complex tasks into more efficient workflows and providing actionable stakeholder insights. Despite their…

Human-Computer Interaction · Computer Science 2025-05-13 Xiaoshan Huang , Jie Gao , Haolun Wu

The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However,…

Machine Learning · Computer Science 2025-08-28 Zhiwei Li , Yong Hu , Wenqing Wang

Model-based reinforcement learning (MBRL) is recognized with the potential to be significantly more sample-efficient than model-free RL. How an accurate model can be developed automatically and efficiently from raw sensory inputs (such as…

Robotics · Computer Science 2023-05-24 Jun Lv , Yunhai Feng , Cheng Zhang , Shuang Zhao , Lin Shao , Cewu Lu

Recent progress in reinforcement learning with verifiable rewards (RLVR) shows that small, specialized language models (SLMs) can exhibit structured reasoning without relying on large monolithic LLMs. We introduce soft hidden-state…