PARM: Pipeline-Adapted Reward Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fan, Xingyu, Shao, Wei, Liu, Jiacheng, Song, Linqi, Heng, Pheng Ann
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918457063243776
author Fan, Xingyu
Shao, Wei
Liu, Jiacheng
Song, Linqi
Heng, Pheng Ann
author_facet Fan, Xingyu
Shao, Wei
Liu, Jiacheng
Song, Linqi
Heng, Pheng Ann
contents Reward models (RMs) are central to aligning large language models (LLMs) with human preferences, powering RLHF and advanced decoding strategies. While most prior work focuses on single-step generation, real-world applications increasingly adopt multi-stage LLM pipelines, where effective reward guidance remains underexplored. We investigate this through code generation for combinatorial optimization, constructing a pipeline that integrates reward models into both formulation and solution stages. We identify a critical challenge: inconsistency between reward model predictions and actual pipeline execution outcomes. To address this, we propose the Pipeline-Adapted Reward Model (PARM), which leverages pipeline-specific data and direct preference optimization to align rewards with downstream feedback. We instantiate PARM as a two-stage pipeline (formulation -> code generation) and evaluate it on four public optimization benchmarks, measuring execution rate and solving accuracy against baselines and sampling methods. A supplementary cross-domain experiment on GSM8K assesses transferability. Results demonstrate that PARM consistently improves pipeline output quality and stability, providing new insights into reward modeling for multi-stage LLM reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18327
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PARM: Pipeline-Adapted Reward Model
Fan, Xingyu
Shao, Wei
Liu, Jiacheng
Song, Linqi
Heng, Pheng Ann
Artificial Intelligence
Computation and Language
Reward models (RMs) are central to aligning large language models (LLMs) with human preferences, powering RLHF and advanced decoding strategies. While most prior work focuses on single-step generation, real-world applications increasingly adopt multi-stage LLM pipelines, where effective reward guidance remains underexplored. We investigate this through code generation for combinatorial optimization, constructing a pipeline that integrates reward models into both formulation and solution stages. We identify a critical challenge: inconsistency between reward model predictions and actual pipeline execution outcomes. To address this, we propose the Pipeline-Adapted Reward Model (PARM), which leverages pipeline-specific data and direct preference optimization to align rewards with downstream feedback. We instantiate PARM as a two-stage pipeline (formulation -> code generation) and evaluate it on four public optimization benchmarks, measuring execution rate and solving accuracy against baselines and sampling methods. A supplementary cross-domain experiment on GSM8K assesses transferability. Results demonstrate that PARM consistently improves pipeline output quality and stability, providing new insights into reward modeling for multi-stage LLM reasoning.
title PARM: Pipeline-Adapted Reward Model
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2604.18327