Summary
This paper introduces Skill Reward Model (Skill-RM), a unified framework that reformulates reward modeling for large language model (LLM) post-training as the execution of a reusable Reward-Evaluation Skill. Current reward evaluation depends on heterogeneous criteria, including rule-based verifiers, ground-truth references, procedural checklists, and complex rubrics, yet no unified mechanism integrates these evidence types. Skill-RM treats reward computation as a structured agentic task, offering a consistent interface to orchestrate heterogeneous resources. It dynamically selects and aggregates evidence tailored to the requirements of each input, moving beyond static evaluation to ensure consistency and transparency across diverse tasks. The approach targets improved feedback signals for reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines.
Paper Overview
- Research Area: NLP
- Authors: Tao Chen, Gangwei Jiang, Pengyu Cheng, Siyuan Huang, Yihao Liu, Jingwei Ni, Jiaqi Guo, Mengyu Zhou, Kai Tang, Junling Liu, Qinliang Su, Xiaoxi Jiang, Guanjun Jiang
- Published: 2026-06-02
- arXiv: 2606.03980
Abstract
Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines. However, current reward evaluation relies on heterogeneous criteria such as rule-based verifiers, ground-truth references, procedural checklists, and complex rubrics, where a unified mechanism to integrate all types of evidence remains unexplored. To this end, we propose Skill Reward Model (Skill-RM), a unified framework that reformulates reward modeling as the execution of a reusable Reward-Evaluation Skill. By treating reward computation as a structured agentic task, Skill-RM provides a consistent interface to orchestrate heterogeneous resources, dynamically selecting and aggregating evidence tailored to the specific requirements ...
---
*Automatically collected on 2026-06-04*
#paper #arXiv #NLP
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/177980809