English
Related papers

Related papers: ICRL: Learning to Internalize Self-Critique with R…

200 papers

Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Yuetian Du , Yucheng Wang , Rongyu Zhang , Zhijie Xu , Boyu Yang , Ming Kong , Jie Liu , Qiang Zhu

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

Large language models adapt to new tasks through in-context learning (ICL) without parameter updates. Current theoretical explanations for this capability assume test tasks are drawn from a distribution similar to that seen during…

Machine Learning · Computer Science 2026-02-23 Di Zhang

We propose to improve in-context learning (ICL) by optimizing the continuous embeddings of a fixed few-shot prompt at test time. The key observation is that the log-probabilities a model assigns to its demonstrated…

Computation and Language · Computer Science 2026-05-25 Baturay Saglam , Dionysis Kalogerias

Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL…

Machine Learning · Computer Science 2026-05-05 Ruiquan Huang , Donghao Li , Yingbin Liang , Jing Yang

Faithfully personalizing large language models (LLMs) to align with individual user preferences is a critical but challenging task. While supervised fine-tuning (SFT) quickly reaches a performance plateau, standard reinforcement learning…

Computation and Language · Computer Science 2025-10-22 Chenghao Zhu , Meiling Tao , Tiannan Wang , Dongyi Ding , Yuchen Eleanor Jiang , Wangchunshu Zhou

Inverse reinforcement learning (IRL) aims to infer an agent's preferences (represented as a reward function $R$) from their behaviour (represented as a policy $\pi$). To do this, we need a behavioural model of how $\pi$ relates to $R$. In…

Machine Learning · Computer Science 2024-03-12 Joar Skalse , Alessandro Abate

In this work, we propose a multi-agent actor-critic reinforcement learning (RL) algorithm to accelerate the multi-level Monte Carlo Markov Chain (MCMC) sampling algorithms. The policies (actors) of the agents are used to generate the…

Machine Learning · Computer Science 2020-11-19 Eric Chung , Yalchin Efendiev , Wing Tat Leung , Sai-Mang Pun , Zecheng Zhang

Autonomous urban driving navigation with complex multi-agent dynamics is under-explored due to the difficulty of learning an optimal driving policy. The traditional modular pipeline heavily relies on hand-designed rules and the…

Computer Vision and Pattern Recognition · Computer Science 2018-07-11 Xiaodan Liang , Tairui Wang , Luona Yang , Eric Xing

Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and instability in replay-based bootstrapped training. In this…

Machine Learning · Computer Science 2026-05-08 Yuan Zhuang , Yuexin Bian , Sihong He , Jie Feng , Qing Su , Songyang Han , Jonathan Petit , Shihao Ji , Yuanyuan Shi , Fei Miao

The ability of large language models (LLMs) to utilize external tools has enabled them to tackle an increasingly diverse range of tasks. However, as the tasks become more complex and long-horizon, the intricate tool utilization process may…

Software Engineering · Computer Science 2025-06-18 Shiting Huang , Zhen Fang , Zehui Chen , Siyu Yuan , Junjie Ye , Yu Zeng , Lin Chen , Qi Mao , Feng Zhao

Large language models (LLMs) have achieved promising results in sentiment analysis through the in-context learning (ICL) paradigm. However, their ability to distinguish subtle sentiments still remains a challenge. Inspired by the human…

Computation and Language · Computer Science 2024-06-06 Hongling Xu , Qianlong Wang , Yice Zhang , Min Yang , Xi Zeng , Bing Qin , Ruifeng Xu

Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already…

Artificial Intelligence · Computer Science 2025-10-02 Guobin Shen , Dongcheng Zhao , Haibo Tong , Jindong Li , Feifei Zhao , Yi Zeng

Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and…

Machine Learning · Computer Science 2025-02-18 Mauricio Tec , Guojun Xiong , Haichuan Wang , Francesca Dominici , Milind Tambe

Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, causing wasted computation, reduced readability, and…

Computation and Language · Computer Science 2025-05-26 Razvan-Gabriel Dumitru , Darius Peteleaza , Vikas Yadav , Liangming Pan

Reinforcement Learning (RL) has been witnessed its potential for training a dialogue policy agent towards maximizing the accumulated rewards given from users. However, the reward can be very sparse for it is usually only provided at the end…

Computation and Language · Computer Science 2021-11-03 Hongru Wang , Huimin Wang , Zezhong Wang , Kam-Fai Wong

We introduce SIRI, Scaling Iterative Reinforcement Learning with Interleaved Compression, a simple yet effective RL approach for Large Reasoning Models (LRMs) that enables more efficient and accurate reasoning. Existing studies have…

Machine Learning · Computer Science 2025-09-30 Haoming Wen , Yushi Bai , Juanzi Li , Jie Tang

We study inverse reinforcement learning (IRL) and imitation learning (IM), the problems of recovering a reward or policy function from expert's demonstrated trajectories. We propose a new way to improve the learning process by adding a…

Machine Learning · Computer Science 2022-08-23 The Viet Bui , Tien Mai , Patrick Jaillet

Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer…

Machine Learning · Computer Science 2019-09-27 Siddharth Reddy , Anca D. Dragan , Sergey Levine

What if artificial intelligence could not only solve problems for which it was trained but also learn to teach itself to solve new problems (i.e., meta-learn)? In this study, we demonstrate that a pre-trained transformer fine-tuned with…

Machine Learning · Computer Science 2025-01-27 Micah Rentschler , Jesse Roberts