Adaptive Reasoning Executor: A Collaborative Agent System for Efficient Reasoning
This incremental improvement addresses efficiency for users of LLM-based reasoning systems.
The paper tackles the computational expense of deep reasoning in LLMs by proposing a collaborative agent system where a small LLM generates initial answers and a large LLM verifies or performs reasoning, reducing large LLM computational cost by over 50% for simple problems with minimal accuracy loss.
Recent advances in Large Language Models (LLMs) demonstrate that chain-of-thought prompting and deep reasoning substantially enhance performance on complex tasks, and multi-agent systems can further improve accuracy by enabling model debates. However, applying deep reasoning to all problems is computationally expensive. To mitigate these costs, we propose a complementary agent system integrating small and large LLMs. The small LLM first generates an initial answer, which is then verified by the large LLM. If correct, the answer is adopted directly; otherwise, the large LLM performs in-depth reasoning. Experimental results show that, for simple problems, our approach reduces the computational cost of the large LLM by more than 50% with negligible accuracy loss, while consistently maintaining robust performance on complex tasks.