Saved in:
Bibliographic Details
Main Authors: Liu, Yuchen, Feng, Yingjie, Qin, Lixiong, Chen, Jiasi, Yu, Jianing, Gao, Sheng, Yang, Sheng, Xu, Weiran
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.29697
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916059299184640
author Liu, Yuchen
Feng, Yingjie
Qin, Lixiong
Chen, Jiasi
Yu, Jianing
Gao, Sheng
Yang, Sheng
Xu, Weiran
author_facet Liu, Yuchen
Feng, Yingjie
Qin, Lixiong
Chen, Jiasi
Yu, Jianing
Gao, Sheng
Yang, Sheng
Xu, Weiran
contents In Agentic Search, trajectory-level outcome rewards fail to quantify the behavioral contributions of individual steps, while existing step-level reward methods typically rely on costly tree sampling. We view world knowledge as a latent world graph and each IS task as search within a latent task graph, where effective steps should make graph progress toward the answer node. Based on this prior, we propose Graph-Distance Contribution Reward (GDCR), a step-level process reward that scores newly-retrieved and newly-cited entities by their distance to the answer node in a training-time Entity-Relation (ER) graph. We further propose Step Advantage Policy Optimization (SAPO), which converts GDCR into step-level advantages and combines them with trajectory-level outcome advantages. Experiments on four challenging benchmarks validate the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29697
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling
Liu, Yuchen
Feng, Yingjie
Qin, Lixiong
Chen, Jiasi
Yu, Jianing
Gao, Sheng
Yang, Sheng
Xu, Weiran
Artificial Intelligence
In Agentic Search, trajectory-level outcome rewards fail to quantify the behavioral contributions of individual steps, while existing step-level reward methods typically rely on costly tree sampling. We view world knowledge as a latent world graph and each IS task as search within a latent task graph, where effective steps should make graph progress toward the answer node. Based on this prior, we propose Graph-Distance Contribution Reward (GDCR), a step-level process reward that scores newly-retrieved and newly-cited entities by their distance to the answer node in a training-time Entity-Relation (ER) graph. We further propose Step Advantage Policy Optimization (SAPO), which converts GDCR into step-level advantages and combines them with trajectory-level outcome advantages. Experiments on four challenging benchmarks validate the effectiveness of our method.
title Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling
topic Artificial Intelligence
url https://arxiv.org/abs/2605.29697