AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling

Yizhi LI, Qingshui Gu, Zhoufutu Wen, Ziniu Li, Ruibin Yuan, Tianshun Xing, Shuyue Guo, Tuney Zheng, Xin Zhou, Xingwei Qu, Wangchunshu Zhou, Zheng Zhang and 7 more

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 TreePO tree sampling to GRPO (ablation)GRPO · Overall (5 math benchmarks)Maj@16 accuracy: 46.63% -> 54.61%Improved
add TreePO advantage estimator on top of tree sampling (Fixed Init Divergence) (ablation)TreePO sampling · Overall (5 math benchmarks)Maj@16 accuracy: 2.27% ↑Improved
add TreePO advantage estimator on top of tree sampling (More Init Divergence) (ablation)TreePO sampling · Overall (5 math benchmarks)Maj@16 accuracy: 3.6% ↑Improved
use tree sampling b=2 instead of sequential (Fixed Init Divergence)TreePO Fixed Init Divergence · Overall Maj@16 and GPU hoursGPU hours: 5.78 -> 4.29 (↓26%)Improved
use tree sampling b=2 instead of sequential (More Init Divergence)TreePO More Init Divergence · Overall Maj@16 and GPU hoursMaj@16 accuracy and GPU hours: 58.21% -> 54.67%; 6.40 -> 3.65 (↓43%)Mixed
use tree sampling b=8 instead of sequential (More Init Divergence)TreePO More Init Divergence · Overall Maj@16 and GPU hoursMaj@16 accuracy and GPU hours: 58.21% -> 58.06%; 6.40 -> 5.05 (↓22%)Mixed
use tree sampling b=4 instead of sequential (Fixed Init Divergence)TreePO Fixed Init Divergence · Overall Maj@16 and GPU hoursMaj@16 accuracy and GPU hours: 56.88% -> 57.50%; 5.78 -> 4.82 (↓17%)Mixed
replace size-weighted subgroup aggregation with simple averaging (ablation)TreePO advantage · MATH and AIME training curvesaccuracy, entropyImproved
add subgroup-level dynamic rejection sampling (ablation)TreePO advantage · MATH and AIME training curvesaccuracyHurt
drop the root-group advantage term (ablation)TreePO advantage · MATH and AIME training curvesaccuracyNo clear effect
misaligned 512-token fallback with 7x1024 segments (ablation)TreePO sampling · AIME training curveAIME accuracy, response lengthHurt
use 14x512 depth-segment instead of 7x1024 (ablation)TreePO with size-weighted advantage · MATH and AIME training curvesaccuracyImproved

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