f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Haldar, Rajdeep, Mei, Lantao, Lin, Guang, Xing, Yue, Song, Qifan
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917478714572800
author Haldar, Rajdeep
Mei, Lantao
Lin, Guang
Xing, Yue
Song, Qifan
author_facet Haldar, Rajdeep
Mei, Lantao
Lin, Guang
Xing, Yue
Song, Qifan
contents Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However, this view has so far been limited to preference-based supervision. We extend it to general LLM alignment, including reinforcement learning with verifiable rewards (RLVR), where alignment feedback is given only as scalar rewards. We introduce $f$-Group Relative Policy Optimization ($f$-GRPO), a class of on-policy RL objectives, and $f$-Hybrid Alignment Loss ($f$-HAL), which combines on-policy reward optimization with off-policy preference supervision. We show that these objectives estimate $f$-divergences between reward-aligned & reward-unaligned distributions induced by above- & below-average reward responses, and prove expected reward improvement after alignment. Empirically, $f$-GRPO improves over GRPO on math-reasoning RLVR tasks, while hybrid $f$-HAL mitigates reward hacking in on-policy safety alignment when verifiable rewards are unavailable and learned reward models must be used.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05946
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
Haldar, Rajdeep
Mei, Lantao
Lin, Guang
Xing, Yue
Song, Qifan
Machine Learning
Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However, this view has so far been limited to preference-based supervision. We extend it to general LLM alignment, including reinforcement learning with verifiable rewards (RLVR), where alignment feedback is given only as scalar rewards. We introduce $f$-Group Relative Policy Optimization ($f$-GRPO), a class of on-policy RL objectives, and $f$-Hybrid Alignment Loss ($f$-HAL), which combines on-policy reward optimization with off-policy preference supervision. We show that these objectives estimate $f$-divergences between reward-aligned & reward-unaligned distributions induced by above- & below-average reward responses, and prove expected reward improvement after alignment. Empirically, $f$-GRPO improves over GRPO on math-reasoning RLVR tasks, while hybrid $f$-HAL mitigates reward hacking in on-policy safety alignment when verifiable rewards are unavailable and learned reward models must be used.
title f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
topic Machine Learning
url https://arxiv.org/abs/2602.05946