Papers
arxiv:2508.21104

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

Published on Aug 28
· Submitted by Nothing2Say on Sep 2
#1 Paper of the day
Authors:
,
,
,

Abstract

PVPO, an enhanced reinforcement learning method using a reference anchor and data pre-sampling, achieves state-of-the-art performance with reduced computational cost and improved generalization.

AI-generated summary

Critic-free reinforcement learning methods, particularly group policies, have attracted considerable attention for their efficiency in complex tasks. However, these methods rely heavily on multiple sampling and comparisons within the policy to estimate advantage, which may cause the policy to fall into local optimum and increase computational cost. To address these issues, we propose PVPO, an efficient reinforcement learning method enhanced by an advantage reference anchor and data pre-sampling. Specifically, we use the reference model to rollout in advance and employ the calculated reward score as a reference anchor. Our approach effectively corrects the cumulative bias introduced by intra-group comparisons and significantly reduces reliance on the number of rollouts. Meanwhile, the reference model can assess sample difficulty during data pre-sampling, enabling effective selection of high-gain data to improve training efficiency. Experiments conducted on nine datasets across two domains demonstrate that PVPO achieves State-Of-The-Art (SOTA) performance. Our approach not only demonstrates robust generalization across multiple tasks, but also exhibits scalable performance across models of varying scales.

Community

Paper author Paper submitter

PVPO, an efficient reinforcement learning method enhanced by an advantage reference anchor and data pre-sampling.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.21104 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.21104 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.21104 in a Space README.md to link it from this page.

Collections including this paper 1