cs.AIJun 7, 2026

PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR

Authors: Shumeng YangYisu LiuJiayi ZhengZhaohui YangLinjing Li

Organizations: Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · School of Artificial Intelligence, Beijing University of Posts and Telecommunications · Institute of Computing Technology, Chinese Academy of Sciences · School of Computer Science and Technology, University of Chinese Academy of Sciences

Abstract

Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning but often suffers from rapid policy-entropy collapse, where the policy prematurely concentrates on narrow high-probability reasoning paths. While global entropy regularization can encourage exploration, uniformly increasing entropy across all token positions is inefficient for long reasoning trajectories, where many tokens are not decision-relevant. We propose Position-Aware Entropy Calibration (PAEC), a token-level entropy-management framework that constructs a soft mask from local top-p entropy and top-two candidate competition, and applies an anchor-based lower-bound penalty to prevent selected-position entropy collapse. Experiments on five mathematical reasoning benchmarks show that PAEC improves macro-average majority-vote performance over strong RLVR baselines, with clear gains on AIME-style tasks. Our results suggest that entropy management in reasoning RL should be formulated as selective exploration allocation over decision-sensitive positions rather than uniform randomness injection.

Explore similar work

CardsList