English
Related papers

Related papers: Reinforced Language Models for Sequential Decision…

200 papers

Recent studies have uncovered the potential of Large Language Models (LLMs) in addressing complex sequential decision-making tasks through the provision of high-level instructions. However, LLM-based agents lack specialization in tackling…

Artificial Intelligence · Computer Science 2024-05-28 Zihao Zhou , Bin Hu , Chenyang Zhao , Pu Zhang , Bin Liu

Large language models (LLMs) augmented with external tools are increasingly deployed as deep research agents that gather, reason over, and synthesize web information to answer complex queries. Although recent open-source systems achieve…

Artificial Intelligence · Computer Science 2026-02-24 Yi Wan , Jiuqi Wang , Liam Li , Jinsong Liu , Ruihao Zhu , Zheqing Zhu

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…

Computation and Language · Computer Science 2024-08-08 Xinyi Wang , Lucas Caccia , Oleksiy Ostapenko , Xingdi Yuan , William Yang Wang , Alessandro Sordoni

Agents significantly enhance the capabilities of standalone Large Language Models (LLMs) by perceiving environments, making decisions, and executing actions. However, LLM agents still face challenges in tasks that require multiple…

Artificial Intelligence · Computer Science 2024-09-17 Yuanzhao Zhai , Tingkai Yang , Kele Xu , Feng Dawei , Cheng Yang , Bo Ding , Huaimin Wang

Language model (LM) pre-training is useful in many language processing tasks. But can pre-trained LMs be further leveraged for more general machine learning problems? We propose an approach for using LMs to scaffold learning and…

We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal. Current approaches commonly train reward models from human preferences, which may then be bottlenecked by…

Computation and Language · Computer Science 2025-03-31 Weizhe Yuan , Richard Yuanzhe Pang , Kyunghyun Cho , Xian Li , Sainbayar Sukhbaatar , Jing Xu , Jason Weston

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising approach to improve the reasoning abilities of Large Language Models (LLMs). Among RLVR algorithms, Group Relative Policy Optimization (GRPO) and its variants…

Artificial Intelligence · Computer Science 2026-04-21 Zhaokang Liao , Yingguo Gao , Yi Yang , Yongheng Hu , Jingting Ding

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

Training large language models (LLMs) as interactive agents for controlling graphical user interfaces (GUIs) presents a unique challenge to optimize long-horizon action sequences with multimodal feedback from complex environments. While…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Fanbin Lu , Zhisheng Zhong , Shu Liu , Chi-Wing Fu , Jiaya Jia

Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs), though they often underperform in specific areas like reasoning. Past methods for enhancing SLMs' reasoning, such as…

Computation and Language · Computer Science 2024-12-12 Kaiyuan Chen , Jin Wang , Xuejie Zhang

Existing research on large language models (LLMs) shows that they can solve information extraction tasks through multi-step planning. However, their extraction behavior on complex sentences and tasks is unstable, emerging issues such as…

Computation and Language · Computer Science 2024-08-30 Zepeng Ding , Ruiyang Ke , Wenhao Huang , Guochao Jiang , Yanda Li , Deqing Yang , Jiaqing Liang

Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. Traditional approaches often depend on meticulously designed prompts, high-quality examples, or additional reward models for…

Machine Learning · Computer Science 2024-06-07 Muning Wen , Junwei Liao , Cheng Deng , Jun Wang , Weinan Zhang , Ying Wen

Large language models (LLMs) are versatile, yet their deployment in complex real-world settings is limited by static knowledge cutoffs and the difficulty of producing controllable behavior within a single inference. Multi-agent search…

Machine Learning · Computer Science 2026-04-21 Guanzhong Chen , Shaoxiong Yang , Chao Li , Wei Liu , Jian Luan , Zenglin Xu

RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across diverse tasks. A straightforward multi-task adaptation of…

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

Machine Learning · Computer Science 2025-10-01 Animesh Jha , Harshit Gupta , Ananjan Nandi

It is crucial for large language models (LLMs) to follow instructions that involve multiple constraints. However, it is an unexplored area to enhance LLMs' ability to follow soft constraints. To bridge the gap, we initially design a…

Computation and Language · Computer Science 2025-06-03 Qingyu Ren , Jie Zeng , Qianyu He , Jiaqing Liang , Yanghua Xiao , Weikang Zhou , Zeye Sun , Fei Yu

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

Machine Learning · Computer Science 2025-12-22 Mingyu Su , Jian Guan , Yuxian Gu , Minlie Huang , Hongning Wang

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches.…

Machine Learning · Computer Science 2026-04-21 Yifeng Ding , Hung Le , Songyang Han , Kangrui Ruan , Zhenghui Jin , Varun Kumar , Zijian Wang , Anoop Deoras

Post-training alignment of large language models (LLMs) is a critical challenge, as not all tokens contribute equally to model performance. This paper introduces a selective alignment strategy that prioritizes high-impact tokens within…

Computation and Language · Computer Science 2025-07-11 Zhijin Dong

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…

Computation and Language · Computer Science 2024-03-29 Hao Lang , Fei Huang , Yongbin Li