English
Related papers

Related papers: Learning What Matters Now: A Dual-Critic Context-A…

200 papers

Tool-Integrated Reasoning (TIR) with search engines enables large language models to iteratively retrieve up-to-date external knowledge, enhancing adaptability and generalization in complex question-answering tasks. However, existing search…

Computation and Language · Computer Science 2025-11-18 Yaocheng Zhang , Haohuan Huang , Zijun Song , Yuanheng Zhu , Qichao Zhang , Zijie Zhao , Dongbin Zhao

Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models, yet its effectiveness remains limited in complex, multi-step reasoning scenarios. Recent efforts have incorporated…

Computation and Language · Computer Science 2025-12-29 Wenda Wei , Yu-An Liu , Ruqing Zhang , Jiafeng Guo , Lixin Su , Shuaiqiang Wang , Dawei Yin , Maarten de Rijke , Xueqi Cheng

Current Reinforcement Learning (RL) methods often suffer from sample-inefficiency, resulting from blind exploration strategies that neglect causal relationships among states, actions, and rewards. Although recent causal approaches aim to…

Artificial Intelligence · Computer Science 2025-02-17 Hongye Cao , Fan Feng , Tianpei Yang , Jing Huo , Yang Gao

In this paper, we present an adherence-aware reinforcement learning (RL) approach aimed at seeking optimal lane-changing recommendations within a semi-autonomous driving environment to enhance a single vehicle's travel efficiency. The…

Machine Learning · Computer Science 2025-04-30 Weihao Sun , Heeseung Bang , Andreas A. Malikopoulos

Retrieval-augmented generation (RAG) connects large language models (LLMs) to external knowledge, but single-round retrieval is often insufficient for complex multi-hop questions. To enhance search capabilities for complex tasks, most…

Computation and Language · Computer Science 2026-05-27 Kun Chen , Qingchao Kong , Zhao Feifei , Wenji Mao

This paper introduces CRITICAL, a novel closed-loop framework for autonomous vehicle (AV) training and testing. CRITICAL stands out for its ability to generate diverse scenarios, focusing on critical driving situations that target specific…

Reinforcement learning (RL) for large language models (LLMs) has shown strong performance in single-turn tasks, but extending it to multi-turn interaction remains challenging due to sparse rewards and poor per-turn credit assignment. In…

Computation and Language · Computer Science 2026-05-06 Naifan Zhang , Ruihan Sun , Jinwei Su , Hengjie Yang , Zhengyuan Pan , Zhaohan Chen , Xiaofan Zhang

In this study, we investigate a context-aware status updating system consisting of multiple sensor-estimator pairs. A centralized monitor pulls status updates from multiple sensors that are monitoring several safety-critical situations…

Information Theory · Computer Science 2023-10-11 Tasmeen Zaman Ornee , Md Kamran Chowdhury Shisher , Clement Kam , Yin Sun

Self-supervised skill learning aims to acquire useful behaviors that leverage the underlying dynamics of the environment. Latent variable models, based on mutual information maximization, have been successful in this task but still struggle…

Machine Learning · Computer Science 2024-03-22 David Emukpere , Bingbing Wu , Julien Perez , Jean-Michel Renders

We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm that tackles a long-standing challenge in continuous-action RL: efficient optimization of an expressive diffusion or flow-matching…

Machine Learning · Computer Science 2026-05-20 Qiyang Li , Sergey Levine

Reinforcement learning (RL) agents often struggle to generalize to new tasks and contexts without updating their parameters, mainly because their learned representations and policies are overfit to the specifics of their training…

Machine Learning · Computer Science 2025-08-12 Fernando Martinez-Lopez , Tao Li , Yingdong Lu , Juntao Chen

Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined with parameter-efficient fine-tuning (PEFT) have shown…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Jiangpeng He , Zhihao Duan , Fengqing Zhu

Meta-Reinforcement Learning (Meta-RL) enables fast adaptation to new testing tasks. Despite recent advancements, it is still challenging to learn performant policies across multiple complex and high-dimensional tasks. To address this, we…

Machine Learning · Computer Science 2024-12-17 Minjae Cho , Chuangchuang Sun

Lane-changing decisions, which are crucial for autonomous vehicle path planning, face practical challenges due to rule-based constraints and limited data. Deep reinforcement learning has become a major research focus due to its advantages…

Artificial Intelligence · Computer Science 2025-10-27 Xiaojun Bi , Mingjie He , Yiwen Sun

Meta-Reinforcement Learning (Meta-RL) agents can struggle to operate across tasks with varying environmental features that require different optimal skills (i.e., different modes of behaviour). Using context encoders based on contrastive…

Machine Learning · Computer Science 2024-11-07 Xuehui Yu , Mhairi Dunion , Xin Li , Stefano V. Albrecht

Current knowledge-enhanced large language models (LLMs) rely on static, pre-constructed knowledge bases that suffer from coverage gaps and temporal obsolescence, limiting their effectiveness in dynamic information environments. We present…

Machine Learning · Computer Science 2025-10-13 Jing Li , Zhijie Sun , Zhicheng Zhou , Suming Qiu , Junjie Huang , Haijia Sun , Linyuan Qiu

Model-based reinforcement learning (RL) algorithms designed for handling complex visual observations typically learn some sort of latent state representation, either explicitly or implicitly. Standard methods of this sort do not distinguish…

Robotics · Computer Science 2022-04-20 Homanga Bharadhwaj , Mohammad Babaeizadeh , Dumitru Erhan , Sergey Levine

This study presents a novel computer system performance optimization and adaptive workload management scheduling algorithm based on Q-learning. In modern computing environments, characterized by increasing data volumes, task complexity, and…

Machine Learning · Computer Science 2024-11-11 Pochun Li , Yuyang Xiao , Jinghua Yan , Xuan Li , Xiaoye Wang

Recent state-of-the-art artificial agents lack the ability to adapt rapidly to new tasks, as they are trained exclusively for specific objectives and require massive amounts of interaction to learn new skills. Meta-reinforcement learning…

Machine Learning · Computer Science 2022-03-23 Zhenshan Bing , Lukas Knak , Fabrice Oliver Robin , Kai Huang , Alois Knoll

Multi-Agent Reinforcement Learning (MARL) has emerged as a powerfulparadigm for cooperative decision-making in connected autonomous vehicles(CAVs); however, existing approaches often fail to guarantee stability, optimality,and…

General Mathematics · Mathematics 2025-11-25 Mazyar Taghavi , Javad Vahidi