(논문 요약) QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management (Paper)
핵심 내용
- 모델: Qwen3-30B-A3B-Thinking
- long document -> 32K 단위 chunk -> memory 를 계속 업데이트.
- corpus+모델로 데이터 생성.

(논문 요약) QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management (Paper)
