AIBullisharXiv – CS AI · 7h ago7/10
🧠
Inducing Reasoning Primitives from Agent Traces
Researchers introduce Reasoning Primitive Induction, a method that extracts reusable reasoning patterns from ReAct-style LLM agent traces and converts them into a compact library of pseudo-tools. The induced libraries consistently outperform the original agents by 22-44 percentage points across multiple reasoning tasks, suggesting a systematic path to improve LLM reasoning through learned decomposition.