Saved in:
Bibliographic Details
Main Authors: Cen, Zhepeng, Yao, Yihang, Han, William, Liu, Zuxin, Zhao, Ding
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.18917
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915532358287360
author Cen, Zhepeng
Yao, Yihang
Han, William
Liu, Zuxin
Zhao, Ding
author_facet Cen, Zhepeng
Yao, Yihang
Han, William
Liu, Zuxin
Zhao, Ding
contents Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RL finetuning: some show substantial performance gains, while others plateau or even degrade. To understand this divergence, we analyze the per-step influence of the RL objective and identify two key conditions for effective post-training: (1) RL-informative rollout accuracy, and (2) strong data co-influence, which quantifies how much the training data affects performance on other samples. Guided by these insights, we propose behavior injection, a task-agnostic data augmentation scheme applied prior to RL. Behavior injection enriches the supervised finetuning (SFT) data by seeding exploratory and exploitative behaviors, effectively making the model more RL-ready. We evaluate our method across two reasoning benchmarks with multiple base models. The results demonstrate that our theoretically motivated augmentation can significantly increase the performance gain from RL over the pre-RL model.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18917
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Behavior Injection: Preparing Language Models for Reinforcement Learning
Cen, Zhepeng
Yao, Yihang
Han, William
Liu, Zuxin
Zhao, Ding
Machine Learning
Artificial Intelligence
Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RL finetuning: some show substantial performance gains, while others plateau or even degrade. To understand this divergence, we analyze the per-step influence of the RL objective and identify two key conditions for effective post-training: (1) RL-informative rollout accuracy, and (2) strong data co-influence, which quantifies how much the training data affects performance on other samples. Guided by these insights, we propose behavior injection, a task-agnostic data augmentation scheme applied prior to RL. Behavior injection enriches the supervised finetuning (SFT) data by seeding exploratory and exploitative behaviors, effectively making the model more RL-ready. We evaluate our method across two reasoning benchmarks with multiple base models. The results demonstrate that our theoretically motivated augmentation can significantly increase the performance gain from RL over the pre-RL model.
title Behavior Injection: Preparing Language Models for Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.18917