English
Related papers

Related papers: Reinforcement World Model Learning for LLM-based A…

200 papers

Large language models (LLMs)-empowered web agents enables automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on supervised fine-tuning (SFT) often struggle with generalization…

Computation and Language · Computer Science 2025-06-10 Yuchen Zhuang , Di Jin , Jiaao Chen , Wenqi Shi , Hanrui Wang , Chao Zhang

Text-based games provide an interactive way to study natural language processing. While deep reinforcement learning has shown effectiveness in developing the game playing agent, the low sample efficiency and the large action space remain to…

Computation and Language · Computer Science 2022-04-22 Yunqiu Xu , Meng Fang , Ling Chen , Yali Du , Joey Tianyi Zhou , Chengqi Zhang

Credit assignment, the process of attributing credit or blame to individual agents for their contributions to a team's success or failure, remains a fundamental challenge in multi-agent reinforcement learning (MARL), particularly in…

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Machine Learning · Computer Science 2024-05-16 Xingzhou Lou , Junge Zhang , Ziyan Wang , Kaiqi Huang , Yali Du

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

Machine Learning · Computer Science 2021-06-03 Sindhu Padakandla

The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks. In this study, we employ ``Introspective Tips" to facilitate LLMs in…

Artificial Intelligence · Computer Science 2023-05-22 Liting Chen , Lu Wang , Hang Dong , Yali Du , Jie Yan , Fangkai Yang , Shuang Li , Pu Zhao , Si Qin , Saravan Rajmohan , Qingwei Lin , Dongmei Zhang

Reinforcement Learning (RL) is a promising approach for solving various control, optimization, and sequential decision making tasks. However, designing reward functions for complex tasks (e.g., with multiple objectives and safety…

Artificial Intelligence · Computer Science 2021-07-23 Xuan Zhao , Marcos Campos

The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries…

Computation and Language · Computer Science 2025-03-04 Shangding Gu , Alois Knoll , Ming Jin

When learning to behave in a stochastic environment where safety is critical, such as driving a vehicle in traffic, it is natural for human drivers to plan fallback strategies as a backup to use if ever there is an unexpected change in the…

Machine Learning · Computer Science 2022-04-12 Ugo Lecerf , Christelle Yemdji-Tchassi , Sébastien Aubert , Pietro Michiardi

Large Language Models (LLMs) possess extensive knowledge and commonsense reasoning capabilities, making them valuable for creating powerful agents. However, existing LLM agent frameworks have not fully utilized past experiences for…

Computation and Language · Computer Science 2025-05-28 Yufei Xiang , Yiqun Shen , Yeqin Zhang , Cam-Tu Nguyen

General-purpose control demands agents that act across many tasks and embodiments, yet research on reinforcement learning (RL) for continuous control remains dominated by single-task or offline regimes, reinforcing a view that online RL…

Machine Learning · Computer Science 2025-12-03 Nicklas Hansen , Hao Su , Xiaolong Wang

In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs) for…

Machine Learning · Computer Science 2026-02-23 Narjes Nourzad , Carlee Joe-Wong

World models improve a learning agent's ability to efficiently operate in interactive and situated environments. This work focuses on the task of building world models of text-based game environments. Text-based games, or interactive…

Machine Learning · Computer Science 2021-10-22 Prithviraj Ammanabrolu , Mark O. Riedl

Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functions, prior work on the topic has proposed several methods…

Machine Learning · Computer Science 2018-10-16 Daiki Kimura , Subhajit Chaudhury , Ryuki Tachibana , Sakyasingha Dasgupta

The advent of large language models (LLMs) has transformed information access and reasoning through open-ended natural language interaction. However, LLMs remain limited by static knowledge, factual hallucinations, and the inability to…

Artificial Intelligence · Computer Science 2025-10-29 Minhua Lin , Zongyu Wu , Zhichao Xu , Hui Liu , Xianfeng Tang , Qi He , Charu Aggarwal , Hui Liu , Xiang Zhang , Suhang Wang

Leveraging multiple large language models (LLMs) to build collaborative multi-agentic workflows has demonstrated significant potential. However, most previous studies focus on prompting the out-of-the-box LLMs, relying on their innate…

Artificial Intelligence · Computer Science 2025-07-15 Chanwoo Park , Seungju Han , Xingzhi Guo , Asuman Ozdaglar , Kaiqing Zhang , Joo-Kyung Kim

Current Large Language Models (LLMs) exhibit a critical modal disconnect: they possess vast semantic knowledge but lack the procedural grounding to respect the immutable laws of the physical world. Consequently, while these agents…

Computation and Language · Computer Science 2026-01-21 Baochang Ren , Yunzhi Yao , Rui Sun , Shuofei Qiao , Ningyu Zhang , Huajun Chen

Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others. In…

We propose a large language model based reward decomposition framework for aligning dialogue agents using only a single session-level feedback signal. We leverage the reasoning capabilities of a frozen, pretrained large language model (LLM)…

Computation and Language · Computer Science 2026-02-12 Dong Won Lee , Hae Won Park , Cynthia Breazeal , Louis-Philippe Morency

World models have been emerging as critical components for assessing the consequences of actions generated by interactive agents in online planning and offline evaluation. In text-based environments, world models are typically evaluated and…