Adaptive Multi-Expert Reasoning via Difficulty-Aware Routing and Uncertainty-Guided Aggregation
For researchers working on math reasoning in LLMs, this work demonstrates that difficulty-based routing and uncertainty-driven aggregation can improve performance without synthetic data, though the gain is incremental over existing methods.
The paper introduces Adaptive Multi-Expert Reasoning (AMR), a framework that uses difficulty-aware routing and uncertainty-guided aggregation to improve math reasoning in LLMs. On GSM8K, AMR achieves 75.28% accuracy with only original training data, outperforming most 7B models trained on synthetic data.
Large language models (LLMs) demonstrate strong performance in math reasoning benchmarks, but their performance varies inconsistently across problems with varying levels of difficulty. This paper describes Adaptive Multi-Expert Reasoning (AMR), a framework that focuses on problem complexity by reasoning with dynamically adapted strategies. An agile routing system that focuses on problem text predicts problems' difficulty and uncertainty and guides a reconfigurable sampling mechanism to manage the breadth of generation. Three specialized experts create candidate responses, which are modified during multiple correction and finalization phases. A neural verifier assesses the correctness of responses, while a clustering-based aggregation technique identifies the final candidate answer based on a combination of consensus and answer quality. When evaluated on the GSM8K dataset, AMR achieved 75.28% accuracy while only using the original training data. This result outperformed the majority of comparable 7B models that were trained on synthetic data. This showcases that models using difficulty-based routing and uncertainty-driven aggregation are efficient and effective in improving math reasoning models' robustness.