Papers by Weida Wang
Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Large reasoning models that use long chain-of-thought excel at problem-solving but waste computational resources. |
| Approach: | They propose a framework that internalizes dynamic early-exit capabilities directly into the model. |
| Outcome: | The proposed framework reduces token consumption by 32.0% on a Qwen3-8B model compared to the vanilla model . |