AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Group-Normalized Implicit Value Optimization for Language Models

Yunseon Choi, Junyoung Jang, Chaeyoung Oh, Minchan Jeong, Doo Hwan Hwang, Kee-Eung Kim

ICLR 2026 · Reinforcement learning › RL from feedback · approach: RL for LLM reasoning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
sequential step-level objective instead of one-step variant (ablation)GN-IVO · Helpful assistant (Llama-3.2-3B-Instruct)Avg@1: 2.562 -> 3.370Improved
sequential step-level objective instead of one-step variant (ablation)GN-IVO · Helpful assistant (Qwen2.5-1.5B-Instruct)Avg@1: 1.446 -> 1.650Improved
sequential step-level objective instead of one-step variant (ablation)GN-IVO · TL;DR (Llama-3.2-3B-Instruct)Avg@1: 3.398 -> 3.347No clear effect
one-step variant of GN-IVO vs GRPO and RLOO (ablation)GN-IVO one-step · Text generation geometric mean (Llama-3.2-3B-Instruct)GM: 1.154 -> 1.478Improved
increase group size K (ablation)GN-IVO and GRPO · HH-RLHF (Qwen2.5-1.5B-Instruct)rewardImproved
small group size K=2 (ablation)GN-IVO vs GRPO · HH-RLHF (Qwen2.5-1.5B-Instruct)rewardImproved
lower temperature alpha 0.1 or 0.2 instead of 0.5 or 1.0 (ablation)GN-IVO · HH-RLHF (Qwen2.5-1.5B-Instruct)reward: alpha 0.5, 1.0 -> 0.1, 0.2Improved
GN-IVO vs GRPOGRPO · AIME2024 (Qwen2.5-Math-7B)Pass@1: 26.6 -> 30.0Improved
GN-IVO vs GRPOGRPO · Olympiad-Bench (Llama-3.1-8B-Instruct)Pass@1: 18.8 -> 17.3Hurt
GN-IVO vs RLOORLOO · AMC2023 (Llama-3.1-8B-Instruct)Pass@1: 35.0 -> 42.5Improved
use explicit value networks (PPO, DRO, OREO)RL baselines · math reasoningPass@1/Pass@3No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy