Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning

About

Context or prompt-level reweighting has emerged as a central algorithmic lever in Reinforcement Learning with Verified Rewards (RLVR) for improving the reasoning capability of large language models, yet the principle determining what constitutes an optimal weighting remains poorly understood. We address this gap by formulating prompt reweighting as a functional derivative of a utility functional defined in the pass-rate function space, yielding a unified optimality framework that accommodates existing schemes, including REINFORCE and GRPO. Building on this optimality framework, we propose a distribution-aware prompt reweighting approach, called CurveRL, based on a quantile coordinate transform, in which the weight assigned to each prompt depends not on the absolute value of pass rates but on its rank and density to reflect the distributional structure of the pass rates in the learning dynamics. Extensive experiments across multiple benchmarks demonstrate that our proposed CurveRL consistently outperforms GRPO and other RLVR baselines. Our study identifies context-distribution control as a principled axis for analyzing and designing prompt-reweighted RLVR algorithms. The code is released in https://github.com/zhyzmath/CurveRL.

Ke Sun, Yizhou Zhao, Jiayi Xin, Qi Long, Weijie Su• 2026

Related benchmarks

TaskDatasetResultRank
Mathematical ReasoningHMMT 25
Pass@19
14
Mathematical ReasoningAIME 2025
Pass@119.6
8
Mathematical ReasoningBeyondAIME
Pass@18.3
8
Mathematical ReasoningHMMT 02 26
Pass@111.9
8
Mathematical ReasoningAverage AIME 2025, BeyondAIME, HMMT 02/25, HMMT 02/26, MATH-500
Pass@126.7
8
Math ReasoningBRUMO 2025
Pass@127.6
8
Math ReasoningHMMT 11/25
Pass@17.2
8
Mathematical ReasoningMATH 500
Pass@184.5
8
Math ReasoningMinerva Math
pass@139.9
8
Mathematical ReasoningBRUMO 2025
Majority@204823.3
4
Showing 10 of 11 rows

Other info

Follow for update