Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
Reasoning language models (RLMs) have demonstrated impressive performance in domains such as mathematics and coding. These domains permit reliable verification of model outputs, which is important for enabling the reinforcement learning that drives RLM performance gains. However, training RLMs on domains that lack reliable verifiers remains challenging. Meanwhile, for both verifiable and unverifiable domains, large amounts of unused supervised fine-tuning data with human-written solutions exist. In this work, we show that these data can be used efficiently to further improve RLM performance. F
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%rasbt/reasoning-from-scratch →
“Fuzzy title match (0.73): “Leveraging Instruction Tuning and Merging for Reasoning Mode” ≈ “rasbt/reasoning-from-scratch””
- LinkedLinked via arxiv author · 85%Yu-Du Feng →
“Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation”
- LinkedLinked via arxiv author · 85%Niels Mündler-Sasahara →
“Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation”
- LinkedLinked via arxiv author · 85%Mark Vero →
“Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation”
- LinkedLinked via arxiv author · 85%Martin Vechev →
“Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation”