الملخص
Generating progressively harder reasoning problems requires synthesis procedures that adapt as the task distribution evolves. Existing task-level recursion reuses generated problems as seeds but leaves the construction harness unchanged. We present task-harness co-evolution, a framework for recursive harness self-improvement (RSI) in reasoning-data synthesis. Online self-improvement converts intermediate solver failures into reusable skills during generation. Post-task self-improvement revises skills, prompts, and workflows after each batch, adopting candidates only when they generate harder valid tasks within a bounded cost increase. Model weights and verification criteria remain fixed. Across mathematics, coding, and science, mean solver accuracy decreases from 100.0% to 54.8% over fourteen evolution rounds. Ablations show that combining both update schedules produces harder tasks than fixed-harness recursion or either schedule alone. The resulting data improves downstream SFT and GRPO performance. In particular, a 27B student fine-tuned on 10K synthesized mathematics examples achieves 62.5% mean-16 accuracy on APEX, competitive with selected frontier-model references. These results support adapting the synthesis harness alongside the tasks to generate increasingly challenging data with downstream training value.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Zhang, W., Jiao, Z., Zhang, C., Jiang, L., Ma, S., Zhang, Q., Chen, G., & Zhang, L. (2026). Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis. https://omanscience.com/ar/articles/recursive-harness-self-improvement-for-frontier-reasoning-data-synthesis
MLA 9
Zhang, Wenlong, et al. "Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis." https://omanscience.com/ar/articles/recursive-harness-self-improvement-for-frontier-reasoning-data-synthesis.
شيكاغو (المؤلف–التاريخ)
Zhang, Wenlong, Zhengbo Jiao, Chenxu Zhang, Lekang Jiang, Siyuan Ma, Qituan Zhang, Guo Chen, and Linfeng Zhang. 2026. "Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis." https://omanscience.com/ar/articles/recursive-harness-self-improvement-for-frontier-reasoning-data-synthesis.
هارفارد
Zhang, W., Jiao, Z., Zhang, C., Jiang, L., Ma, S., Zhang, Q., Chen, G. and Zhang, L. (2026) 'Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis', Available at: https://omanscience.com/ar/articles/recursive-harness-self-improvement-for-frontier-reasoning-data-synthesis.
فانكوفر
Zhang W, Jiao Z, Zhang C, Jiang L, Ma S, Zhang Q, et al. Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis. https://omanscience.com/ar/articles/recursive-harness-self-improvement-for-frontier-reasoning-data-synthesis
IEEE
W. Zhang, Z. Jiao, C. Zhang, L. Jiang, S. Ma, Q. Zhang, G. Chen, and L. Zhang, "Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis," https://omanscience.com/ar/articles/recursive-harness-self-improvement-for-frontier-reasoning-data-synthesis.