English
Related papers

Related papers: Reward Design with Language Models

200 papers

Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…

Artificial Intelligence · Computer Science 2025-02-18 Zhenfang Chen , Delin Chen , Rui Sun , Wenjun Liu , Chuang Gan

Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving.Recent works introduce multi-agent reflection frameworks where multiple LLM agents critique and refine each other's outputs using…

Artificial Intelligence · Computer Science 2025-11-26 Yuanhao Li , Mingshan Liu , Hongbo Wang , Yiding Zhang , Yifei Ma , Wei Tan

Modern large language models (LLMs) are optimized for human-aligned responses using Reinforcement Learning from Human Feedback (RLHF). However, existing RLHF approaches assume a universal preference model and fail to account for individual…

Machine Learning · Computer Science 2025-03-11 Idan Shenfeld , Felix Faltings , Pulkit Agrawal , Aldo Pacchiano

In offline reinforcement learning (RL), learning from fixed datasets presents a promising solution for domains where real-time interaction with the environment is expensive or risky. However, designing dense reward signals for offline…

Machine Learning · Computer Science 2025-04-15 Younghwan Lee , Tung M. Luu , Donghoon Lee , Chang D. Yoo

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

Modern recommender systems aim to improve user experience. As reinforcement learning (RL) naturally fits this objective -- maximizing an user's reward per session -- it has become an emerging topic in recommender systems. Developing…

Information Retrieval · Computer Science 2022-06-16 Xin Xin , Tiago Pimentel , Alexandros Karatzoglou , Pengjie Ren , Konstantina Christakopoulou , Zhaochun Ren

To align conditional text generation model outputs with desired behaviors, there has been an increasing focus on training the model using reinforcement learning (RL) with reward functions learned from human annotations. Under this…

Computation and Language · Computer Science 2023-06-02 Richard Yuanzhe Pang , Vishakh Padmakumar , Thibault Sellam , Ankur P. Parikh , He He

Recent advancements in large language models (LLMs) have enabled understanding webpage contexts, product details, and human instructions. Utilizing LLMs as the foundational architecture for either reward models or policies in reinforcement…

Machine Learning · Computer Science 2024-08-30 Shuang Feng , Grace Feng

We introduce Agent Process Reward Models (AgentPRM), a simple and scalable framework for training LLM agents to continually improve through interactions. AgentPRM follows a lightweight actor-critic paradigm, using Monte Carlo rollouts to…

Machine Learning · Computer Science 2025-02-17 Sanjiban Choudhury

The extraordinary capabilities of large language models (LLMs) such as ChatGPT and GPT-4 are in part unleashed by aligning them with reward models that are trained on human preferences, which are often represented as rankings of responses…

Machine Learning · Computer Science 2025-10-31 Ziang Song , Tianle Cai , Jason D. Lee , Weijie J. Su

Code-generating Large Language Models (LLMs) have become essential tools in modern software development, enhancing productivity and accelerating development. This paper aims to investigate the fine-tuning of code-generating LLMs using…

Software Engineering · Computer Science 2025-05-06 Marina Sakharova , Abhinav Anand , Mira Mezini

Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs). The previous studies have elucidated the merits of integrating feedback or search mechanisms during model inference to improve the…

Computation and Language · Computer Science 2023-10-17 Qianli Ma , Haotian Zhou , Tingkai Liu , Jianbo Yuan , Pengfei Liu , Yang You , Hongxia Yang

Large language models (LLMs) have achieved remarkable success in a wide range of natural language processing tasks and can be adapted through prompting. However, they remain suboptimal in multi-turn interactions, often relying on incorrect…

Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious or undesirable attributes such as length, format, hallucinations, and sycophancy. In this work, we introduce…

Machine Learning · Computer Science 2026-02-18 Atticus Wang , Iván Arcuschin , Arthur Conmy

The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…

Machine Learning · Computer Science 2025-05-21 Yongxin Deng , Xihe Qiu , Jue Chen , Xiaoyu Tan

We introduce a new benchmark for reward models that quantifies their ability to produce strong language models through RLHF (Reinforcement Learning from Human Feedback). The gold-standard approach is to run a full RLHF training pipeline and…

Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks while it remains challenging for them to solve complex multi-step tasks as agents. In practice, agents sensitive to the outcome of certain key steps…

Artificial Intelligence · Computer Science 2025-05-28 Zilong Wang , Jingfeng Yang , Sreyashi Nag , Samarth Varshney , Xianfeng Tang , Haoming Jiang , Jingbo Shang , Sheikh Muhammad Sarwar

Preference-based reinforcement learning (RL) has emerged as a new field in robot learning, where humans play a pivotal role in shaping robot behavior by expressing preferences on different sequences of state-action pairs. However,…

Robotics · Computer Science 2024-02-26 Simon Holk , Daniel Marta , Iolanda Leite

Reward design is a critical part of the application of reinforcement learning, the performance of which strongly depends on how well the reward signal frames the goal of the designer and how well the signal assesses progress in reaching…

Machine Learning · Computer Science 2022-08-01 Yixiang Wang , Yujing Hu , Feng Wu , Yingfeng Chen

Reinforcement Learning (RL) traditionally relies on scalar reward signals, limiting its ability to leverage the rich semantic knowledge often available in real-world tasks. In contrast, humans learn efficiently by combining numerical…

‹ Prev 1 3 4 5 6 7 10 Next ›