AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

UCPO: Uncertainty-Aware Policy Optimization

Xianzhou Zeng, Jing Huang, Chunmei Xie, Gongrui Nan, Siye Chen, Mengyu Lu, Weiqi Xiong, Qixuan Zhou, Junhao Zhang, Qiang Zhu, Yadong Li, Xingzhong Xu

ICML 2026 · Reinforcement learning › RL from feedback · approach: GRPO stability and variants · 0 citations (OpenAlex)

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
add UCPO (TAD + DURA) over GRPOLlama-3.1-8B-Instruct · Math & Text Reasoning (avg)PAQ: 20.06 -> 28.45Improved
add UCPO over GRPOQwen3-8B · General Tasks (avg)PAQ: 73.48 -> 79.68Improved
add UCPO over GRPOQwen3-8B · General Tasks (avg)F1: 73.00 -> 70.79Hurt
replace fixed uncertainty reward (GRPO-UC r_u=0.5) with UCPOLlama-3.1-8B-Instruct · Math & Text Reasoning (avg)F1: 9.01 -> 22.65Improved
use fixed uncertainty reward r_u=0.8 instead of 0.2GRPO-UC on Llama · Math & Text Reasoning (avg)F1: 13.31 -> 4.25Hurt
add Ternary Advantage Decoupling (TAD) (ablation)UCPO on Llama-3.1-8B-Instruct · General TasksPAQ: 51.17 -> 58.58Improved
add DURA reward adjustment (ablation)UCPO on Llama-3.1-8B-Instruct · General TasksF1: 23.41 -> 43.10Improved
add DURA reward adjustment (ablation)UCPO on Llama-3.1-8B-Instruct · General TasksPAQ: 58.96 -> 58.58Hurt
add Non-Ternary Filtering (NTF) (ablation)UCPO on Llama-3.1-8B-Instruct · Math & Text ReasoningF1: 22.93 -> 22.65Improved
add Non-Ternary Filtering (NTF) (ablation)UCPO on Llama-3.1-8B-Instruct · General TasksPAQ: 55.68 -> 58.58Improved
add Low-Resource Extensions (LRE) (ablation)UCPO on Llama-3.1-8B-Instruct · General TasksF1: 39.99 -> 43.10Improved
raise DURA weight w from 1.0 to 2.0 (ablation)UCPO on Llama-3.1-8B-Instruct · General Tasks (avg)PAQ / F1: PAQ 58.58 -> 54.53; F1 43.10 -> 45.05Mixed

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