English
Related papers

Related papers: Every Step Counts: Step-Level Credit Assignment fo…

200 papers

Large language models revolutionize Text2SQL through supervised fine-tuning, yet a crucial limitation is overlooked: the complexity of databases leads to an increased context length, consequently resulting in higher GPU memory demands for…

Databases · Computer Science 2024-10-16 Wen Wuzhenghong , Zhang Yongpan , Pan Su , Sun Yuwei , Lu Pengwei , Ding Cheng

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye

As large language models have evolved, it has become crucial to distinguish between process supervision and outcome supervision -- two key reinforcement learning approaches to complex reasoning tasks. While process supervision offers…

Machine Learning · Computer Science 2025-03-28 Zeyu Jia , Alexander Rakhlin , Tengyang Xie

Large Language Models (LLMs) often generate overly cautious and vague responses on sensitive topics, sacrificing helpfulness for safety. Existing evaluation frameworks lack systematic methods to identify and address specific weaknesses in…

Computation and Language · Computer Science 2026-03-05 Juhyun Oh , Nayeon Lee , Chani Jung , Jiho Jin , Junho Myung , Jongwon Lee , Taeui Song , Alice Oh

Multi-step (also called n-step) methods in reinforcement learning (RL) have been shown to be more efficient than the 1-step method due to faster propagation of the reward signal, both theoretically and empirically, in tasks exploiting…

Artificial Intelligence · Computer Science 2020-06-24 Lingheng Meng , Rob Gorbet , Dana Kulić

Large Language Models (LLMs) have demonstrated remarkable capabilities, enabling language agents to excel at single-turn tasks. However, their application to complex, multi-step, and long-horizon tasks remains challenging. While…

Machine Learning · Computer Science 2025-10-24 Jiazheng Li , Yawei Wang , David Yan , Yijun Tian , Zhichao Xu , Huan Song , Panpan Xu , Lin Lee Cheong

Large Language Models (LLMs) have the potential to automate reward engineering by leveraging their broad domain knowledge across various tasks. However, they often need many iterations of trial-and-error to generate effective reward…

Machine Learning · Computer Science 2024-10-28 Vishnu Sarukkai , Brennan Shacklett , Zander Majercik , Kush Bhatia , Christopher Ré , Kayvon Fatahalian

Recent advances have established a new machine learning paradigm based on scaling up compute at inference time as well as at training time. In that line of work, a combination of Supervised Fine-Tuning (SFT) on synthetic demonstrations and…

Machine Learning · Computer Science 2025-07-08 Corrado Rainone , Tim Bakker , Roland Memisevic

Multi-step reasoning improves the capabilities of large language models (LLMs) but increases the risk of errors propagating through intermediate steps. Process reward models (PRMs) mitigate this by scoring each step individually, enabling…

Computation and Language · Computer Science 2026-03-19 Corentin Royer , Debarun Bhattacharjya , Gaetano Rossiello , Andrea Giovannini , Mennatallah El-Assady

Text-to-SQL aims at generating SQL queries for the given natural language questions and thus helping users to query databases. Prompt learning with large language models (LLMs) has emerged as a recent approach, which designs prompts to lead…

Information Retrieval · Computer Science 2023-09-06 Chunxi Guo , Zhiliang Tian , Jintao Tang , Shasha Li , Zhihua Wen , Kaixuan Wang , Ting Wang

Autoregressive language models are widely used for text evaluation, however, their left-to-right factorization introduces positional bias, i.e., early tokens are scored with only leftward context, conflating architectural asymmetry with…

Computation and Language · Computer Science 2026-05-13 Wen Lai , Yingli Shen , Dingnan Jin , Qing Cui , Jun Zhou , Maosong Sun , Alexander Fraser

Model-based reinforcement learning is an appealing framework for creating agents that learn, plan, and act in sequential environments. Model-based algorithms typically involve learning a transition model that takes a state and an action and…

Machine Learning · Computer Science 2019-06-03 Kavosh Asadi , Dipendra Misra , Seungchan Kim , Michel L. Littman

Reinforcement Learning (RL) heavily relies on the careful design of the reward function. However, accurately assigning rewards to each state-action pair in Long-Term Reinforcement Learning (LTRL) tasks remains a significant challenge. As a…

Machine Learning · Computer Science 2025-06-03 Qi Ju , Falin Hei , Zhemei Fang , Yunfeng Luo

Recent GRPO-based approaches built on flow matching models have shown remarkable improvements in human preference alignment for text-to-image generation. Nevertheless, they still suffer from the sparse reward problem: the terminal reward of…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Haoyou Deng , Keyu Yan , Chaojie Mao , Xiang Wang , Yu Liu , Changxin Gao , Nong Sang

Fine-tuning foundation models has emerged as a powerful approach for generating objects with specific desired properties. Reinforcement learning (RL) provides an effective framework for this purpose, enabling models to generate outputs that…

Machine Learning · Computer Science 2025-11-04 Pouya M. Ghari , Simone Sciabola , Ye Wang

Large language models (LLMs) have demonstrated impressive ability in solving complex mathematical problems with multi-step reasoning and can be further enhanced with well-designed in-context learning (ICL) examples. However, this potential…

Computation and Language · Computer Science 2025-02-18 Beichen Zhang , Yuhong Liu , Xiaoyi Dong , Yuhang Zang , Pan Zhang , Haodong Duan , Yuhang Cao , Dahua Lin , Jiaqi Wang

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Artificial Intelligence · Computer Science 2026-01-30 Zhao Wang , Ziliang Zhao , Zhicheng Dou

In this paper, we present an innovative process-oriented math process reward model called \textbf{Math-Shepherd}, which assigns a reward score to each step of math problem solutions. The training of Math-Shepherd is achieved using…

Artificial Intelligence · Computer Science 2024-02-20 Peiyi Wang , Lei Li , Zhihong Shao , R. X. Xu , Damai Dai , Yifei Li , Deli Chen , Y. Wu , Zhifang Sui

As large language models (LLMs) are increasingly used in Text-to-SQL tasks, Reinforcement Learning (RL) has become a common method for improving performance. Existing methods primarily rely on static execution feedback, which restricts…

Artificial Intelligence · Computer Science 2025-10-30 Zekun Xu , Siyu Xia , Chuhuai Yue , Jiajun Chai , Mingxue Tian , Xiaohan Wang , Wei Lin , Haoxuan Li , Guojun Yin

Text-to-SQL models allow users to interact with a database more easily by generating executable SQL statements from natural-language questions. Despite recent successes on simpler databases and questions, current Text-to-SQL methods still…

Artificial Intelligence · Computer Science 2025-09-10 Heng Hao , Wenjun Hu , Oxana Verkholyak , Davoud Ataee Tarzanagh , Baruch Gutow , Sima Didari , Masoud Faraki , Hankyu Moon , Seungjai Min