InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Chengwei, Kim, Jung-jae, Zhang, Longyin, Chen, Shengkai, Chen, Nancy F.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912972371132416
author Wei, Chengwei
Kim, Jung-jae
Zhang, Longyin
Chen, Shengkai
Chen, Nancy F.
author_facet Wei, Chengwei
Kim, Jung-jae
Zhang, Longyin
Chen, Shengkai
Chen, Nancy F.
contents Large Language Models (LLMs) with extended reasoning capabilities often generate verbose and redundant reasoning traces, incurring unnecessary computational cost. While existing reinforcement learning approaches address this by optimizing final response length, they neglect the quality of intermediate reasoning steps, leaving models vulnerable to reward hacking. We argue that verbosity is not merely a length problem, but a symptom of poor intermediate reasoning quality. To investigate this, we conduct an empirical study tracking the conditional entropy of the answer distribution across reasoning steps. We find that high-quality reasoning traces exhibit two consistent properties: low uncertainty convergence and monotonic progress. These findings suggest that high-quality reasoning traces are informationally dense, that is, each step contributes meaningful entropy reduction relative to the total reasoning length. Motivated by this, we propose InfoDensity, a reward framework for RL training that combines an AUC-based reward and a monotonicity reward as a unified measure of reasoning quality, weighted by a length scaling term that favors achieving equivalent quality more concisely. Experiments on mathematical reasoning benchmarks demonstrate that InfoDensity matches or surpasses state-of-the-art baselines in accuracy while significantly reducing token usage, achieving a strong accuracy-efficiency trade-off.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17310
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
Wei, Chengwei
Kim, Jung-jae
Zhang, Longyin
Chen, Shengkai
Chen, Nancy F.
Artificial Intelligence
Computation and Language
Large Language Models (LLMs) with extended reasoning capabilities often generate verbose and redundant reasoning traces, incurring unnecessary computational cost. While existing reinforcement learning approaches address this by optimizing final response length, they neglect the quality of intermediate reasoning steps, leaving models vulnerable to reward hacking. We argue that verbosity is not merely a length problem, but a symptom of poor intermediate reasoning quality. To investigate this, we conduct an empirical study tracking the conditional entropy of the answer distribution across reasoning steps. We find that high-quality reasoning traces exhibit two consistent properties: low uncertainty convergence and monotonic progress. These findings suggest that high-quality reasoning traces are informationally dense, that is, each step contributes meaningful entropy reduction relative to the total reasoning length. Motivated by this, we propose InfoDensity, a reward framework for RL training that combines an AUC-based reward and a monotonicity reward as a unified measure of reasoning quality, weighted by a length scaling term that favors achieving equivalent quality more concisely. Experiments on mathematical reasoning benchmarks demonstrate that InfoDensity matches or surpasses state-of-the-art baselines in accuracy while significantly reducing token usage, achieving a strong accuracy-efficiency trade-off.
title InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2603.17310