AIBullisharXiv – CS AI · 10h ago7/10
🧠
M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models
Researchers introduce M2A, a novel model merging paradigm that combines mathematical and agentic reasoning in large language models without retraining. The approach improves a Qwen3-8B model's software engineering benchmark performance from 44.0% to 51.2% by strategically injecting mathematical reasoning capabilities along directions that preserve agent behavior.