HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression 事件

HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression arXiv:2606.01934v1 Announce Type: cross Abstract: Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, yet this lengthy process incurs substantial inference overhead. Existing CoT compression methods struggle with inflexible manual length budgets, computationally expensive multi-stage training pipelines, and fragile scalability restricted to small models. We propose HMP