InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |