Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918188038488064 |
|---|---|
| author | Zhao, Bo Kapusuzoglu, Berkcan Balasubramaniam, Kartik Sahu, Sambit Chakraborty, Supriyo Winata, Genta Indra |
| author_facet | Zhao, Bo Kapusuzoglu, Berkcan Balasubramaniam, Kartik Sahu, Sambit Chakraborty, Supriyo Winata, Genta Indra |
| contents | Reasoning language models perform well on complex tasks but are costly to deploy due to their size and long reasoning traces. We propose a routing approach that assigns each problem to the smallest model likely to solve it, reducing compute without sacrificing accuracy. Using intermediate representations from s1.1-32B, we train lightweight predictors of problem difficulty or model correctness to guide routing across a pool of reasoning models. On diverse math benchmarks, routing improves efficiency over random assignment and matches s1.1-32B's performance while using significantly less compute. Our results demonstrate that difficulty-aware routing is effective for cost-efficient deployment of reasoning models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03808 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing Reasoning Efficiency through Prompt Difficulty Prediction Zhao, Bo Kapusuzoglu, Berkcan Balasubramaniam, Kartik Sahu, Sambit Chakraborty, Supriyo Winata, Genta Indra Machine Learning Artificial Intelligence Reasoning language models perform well on complex tasks but are costly to deploy due to their size and long reasoning traces. We propose a routing approach that assigns each problem to the smallest model likely to solve it, reducing compute without sacrificing accuracy. Using intermediate representations from s1.1-32B, we train lightweight predictors of problem difficulty or model correctness to guide routing across a pool of reasoning models. On diverse math benchmarks, routing improves efficiency over random assignment and matches s1.1-32B's performance while using significantly less compute. Our results demonstrate that difficulty-aware routing is effective for cost-efficient deployment of reasoning models. |
| title | Optimizing Reasoning Efficiency through Prompt Difficulty Prediction |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.03808 |