English
Related papers

Related papers: RewardHarness: Self-Evolving Agentic Post-Training

200 papers

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based…

Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm…

Artificial Intelligence · Computer Science 2026-05-26 Erhan Zhang , Yiqun Chen , Zechun Niu , Wei Yang , Xiaochi Wei , Yan Gao , Yi Wu , Yao Hu , Jiaxin Mao

The ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback (RLHF). We propose a data augmentation and expansion framework that…

Machine Learning · Computer Science 2025-06-11 Yiyang Zhao , Huiyu Bai , Xuejiao Zhao

We propose RLAnything, a reinforcement learning framework that dynamically forges environment, policy, and reward models through closed-loop optimization, amplifying learning signals and strengthening the overall RL system for any LLM or…

Machine Learning · Computer Science 2026-02-04 Yinjie Wang , Tianbao Xie , Ke Shen , Mengdi Wang , Ling Yang

High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consuming and costly. Recent methods often adopt a self-rewarding…

Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing…

Machine Learning · Computer Science 2018-08-14 Yuri Burda , Harri Edwards , Deepak Pathak , Amos Storkey , Trevor Darrell , Alexei A. Efros

Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…

Artificial Intelligence · Computer Science 2025-11-12 Dengcan Liu , Jiahao Li , Zheren Fu , Yi Tu , Jiajun Li , Zhendong Mao , Yongdong Zhang

Model-based evaluation is at the heart of successful model development -- as a reward model for training, and as a replacement for human evaluation. To train such evaluators, the standard approach is to collect a large amount of human…

Building neural reward models from human preferences is a pivotal component in reinforcement learning from human feedback (RLHF) and large language model alignment research. Given the scarcity and high cost of human annotation, how to…

Computation and Language · Computer Science 2025-02-10 Yunyi Shen , Hao Sun , Jean-François Ton

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

Computation and Language · Computer Science 2024-01-01 Yaru Hao , Zewen Chi , Li Dong , Furu Wei

Reward functions are central in specifying the task we want a reinforcement learning agent to perform. Given a task and desired optimal behavior, we study the problem of designing informative reward functions so that the designed rewards…

Machine Learning · Computer Science 2024-02-13 Rati Devidze , Parameswaran Kamalaruban , Adish Singla

In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when…

Machine Learning · Computer Science 2025-06-19 Rui Yu , Shenghua Wan , Yucen Wang , Chen-Xiao Gao , Le Gan , Zongzhang Zhang , De-Chuan Zhan

In recent years, work has gone into developing deep interpretable methods for image classification that clearly attributes a model's output to specific features of the data. One such of these methods is the Prototypical Part Network…

Machine Learning · Computer Science 2024-06-05 Aaron J. Li , Robin Netzorg , Zhihan Cheng , Zhuoqin Zhang , Bin Yu

Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs). Traditionally, training these models relies on…

Machine Learning · Computer Science 2024-09-12 Yifei He , Haoxiang Wang , Ziyan Jiang , Alexandros Papangelis , Han Zhao

Large language models are increasingly used as personal assistants, yet most lack a persistent user model, forcing users to repeatedly restate preferences across sessions. We propose Vector-Adapted Retrieval Scoring (VARS), a…

Computation and Language · Computer Science 2026-03-24 Yuren Hao , Shuhaib Mehri , ChengXiang Zhai , Dilek Hakkani-Tür

We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework…

Computation and Language · Computer Science 2024-03-19 Yuhang Lai , Siyuan Wang , Shujun Liu , Xuanjing Huang , Zhongyu Wei

Reinforcement learning (RL) in long horizon and sparse reward tasks is notoriously difficult and requires a lot of training steps. A standard solution to speed up the process is to leverage additional reward signals, shaping it to better…

Computation and Language · Computer Science 2022-10-14 Thomas Carta , Pierre-Yves Oudeyer , Olivier Sigaud , Sylvain Lamprier

Specifying reward functions for complex tasks like object manipulation or driving is challenging to do by hand. Reward learning seeks to address this by learning a reward model using human feedback on selected query policies. This shifts…

Machine Learning · Computer Science 2023-02-27 Kush Bhatia , Wenshuo Guo , Jacob Steinhardt

Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into…

Artificial Intelligence · Computer Science 2024-12-03 Chenliang Li , Siliang Zeng , Zeyi Liao , Jiaxiang Li , Dongyeop Kang , Alfredo Garcia , Mingyi Hong

We investigated Agentic RL with large language models on the \textsc{TravelPlanner} benchmark. Our approach, \textsc{Planner-R1}, achieved a \textbf{56.9\%} final-pass rate with only 180 training queries, a $2.7\times$ improvement over…

Artificial Intelligence · Computer Science 2025-10-03 Siyu Zhu , Yanbin Jiang , Hejian Sang , Shao Tang , Qingquan Song , Biao He , Rohit Jain , Zhipeng Wang , Alborz Geramifard