English
Related papers

Related papers: Critique-RL: Training Language Models for Critiqui…

200 papers

Large Language Models (LLMs) have achieved remarkable advancements in natural language processing tasks, yet they encounter challenges in complex decision-making scenarios that require long-term reasoning and alignment with high-level…

Computation and Language · Computer Science 2025-06-10 Heng Dong , Kefei Duan , Chongjie Zhang

Reinforcement Learning (RL) has empowered Large Language Models (LLMs) with strong reasoning capabilities, but vanilla RL mainly focuses on generation capability improvement by training with only first-order rollout (generating multiple…

Computation and Language · Computer Science 2026-02-27 Zhe Yang , Yudong Wang , Rang Li , Zhifang Sui

As Large Language Models (LLMs) are rapidly evolving, providing accurate feedback and scalable oversight on their outputs becomes an urgent and critical problem. Leveraging LLMs as critique models to achieve automated supervision is a…

Computation and Language · Computer Science 2025-05-02 Wenkai Yang , Jingwen Chen , Yankai Lin , Ji-Rong Wen

Automatic evaluation is crucial yet challenging for open-ended natural language generation, especially when rule-based metrics are infeasible. Compared with traditional methods, the recent LLM-as-a-Judge paradigms enable better and more…

Computation and Language · Computer Science 2026-02-03 Xinyu Hu , Yancheng He , Weixun Wang , Tao Feng , Li Lin , Jiashun Liu , Wenbo Su , Bo Zheng , Xiaojun Wan

Recent reinforcement learning (RL) techniques have yielded impressive reasoning improvements in language models, yet it remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during…

Computation and Language · Computer Science 2025-12-09 Charlie Zhang , Graham Neubig , Xiang Yue

Reinforcement learning with AI feedback (RLAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models. RLAIF first performs supervised fine-tuning (SFT) using demonstrations from a…

Machine Learning · Computer Science 2024-02-20 Archit Sharma , Sedrick Keh , Eric Mitchell , Chelsea Finn , Kushal Arora , Thomas Kollar

Task-oriented dialogue systems aim to fulfill user goals through natural language interactions. They are ideally evaluated with human users, which however is unattainable to do at every iteration of the development phase. Simulated users…

Computation and Language · Computer Science 2022-09-05 Nurul Lubis , Christian Geishauser , Hsien-Chin Lin , Carel van Niekerk , Michael Heck , Shutong Feng , Milica Gašić

Reinforcement learning (RL) is a powerful tool for solving complex decision-making problems, but its lack of transparency and interpretability has been a major challenge in domains where decisions have significant real-world consequences.…

Artificial Intelligence · Computer Science 2023-09-12 Muzhe Guo , Feixu Yu , Tian Lan , Fang Jin

Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards,…

Artificial Intelligence · Computer Science 2025-08-11 Yihao Liu , Shuocheng Li , Lang Cao , Yuhang Xie , Mengyu Zhou , Haoyu Dong , Xiaojun Ma , Shi Han , Dongmei Zhang

Offline-to-online (O2O) reinforcement learning (RL) provides an effective means of leveraging an offline pre-trained policy as initialization to improve performance rapidly with limited online interactions. Recent studies often design…

Machine Learning · Computer Science 2024-12-30 Qin-Wen Luo , Ming-Kun Xie , Ye-Wen Wang , Sheng-Jun Huang

As language models (LMs) demonstrate their capabilities in various fields, their application to tasks requiring multi-round interactions has become increasingly popular. These tasks usually have complex dynamics, so supervised fine-tuning…

Machine Learning · Computer Science 2024-06-07 Runlong Zhou , Simon S. Du , Beibin Li

We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its core is a policy improvement objective that avoids the high variance of typical policy…

Machine Learning · Computer Science 2026-05-25 Lunjun Zhang , Shuo Han , Hanrui Lyu , Bradly C Stadie

Reinforcement Learning (RL) has been shown to improve the capabilities of large language models (LLMs). However, applying RL to open-domain tasks faces two key challenges: (1) the inherent subjectivity of these tasks prevents the verifiable…

Machine Learning · Computer Science 2026-02-26 Weixuan Ou , Yanzhao Zheng , Shuoshuo Sun , Wei Zhang , Baohua Dong , Hangcheng Zhu , Ruohui Huang , Gang Yu , Pengwei Yan , Yifan Qiao

Large language model (LLM) agents -- LLMs that dynamically interact with an environment over long horizons -- have become an increasingly important area of research, enabling automation in complex tasks involving tool-use, web browsing, and…

Machine Learning · Computer Science 2026-02-04 Joey Hong , Kang Liu , Zhan Ling , Jiecao Chen , Sergey Levine

The dataset distributions in offline reinforcement learning (RL) often exhibit complex and multi-modal distributions, necessitating expressive policies to capture such distributions beyond widely-used Gaussian policies. To handle such…

Machine Learning · Computer Science 2026-02-23 Jongseong Chae , Jongeui Park , Yongjae Shin , Gyeongmin Kim , Seungyul Han , Youngchul Sung

Reinforcement Learning (RL) significantly enhances the reasoning abilities of large language models (LLMs), yet applying it to multi-turn agentic tasks remains challenging due to the long-horizon nature of interactions and the stochasticity…

Artificial Intelligence · Computer Science 2026-04-03 Jingyue Gao , Yanjiang Guo , Xiaoshuai Chen , Jianyu Chen

Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving, but adversarial attacks designed to mislead RL systems remain challenging. Existing approaches often rely on modifying the…

Machine Learning · Computer Science 2025-07-25 Junyong Jiang , Buwei Tian , Chenxing Xu , Songze Li , Lu Dong

Actor-critic (AC) methods are widely used in reinforcement learning (RL) and benefit from the flexibility of using any policy gradient method as the actor and value-based method as the critic. The critic is usually trained by minimizing the…

Machine Learning · Computer Science 2023-11-01 Sharan Vaswani , Amirreza Kazemi , Reza Babanezhad , Nicolas Le Roux

While large language models (LLMs) have demonstrated strong performance on complex reasoning tasks such as competitive programming (CP), existing methods predominantly focus on single-attempt settings, overlooking their capacity for…

Artificial Intelligence · Computer Science 2026-04-02 Shaopeng Fu , Xingxing Zhang , Li Dong , Di Wang , Furu Wei

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…

Machine Learning · Computer Science 2021-06-10 Kimin Lee , Laura Smith , Pieter Abbeel