AdaR: A Framework for Equipping LLMs with Adaptive Reasoning
Read the original on arXiv AI →AdaR is a framework designed to enhance large language models (LLMs) with adaptive reasoning for mathematical tasks. It identifies and mitigates spurious reasoning—where models rely on superficial correlations—by generating logically equivalent queries and training with Reinforcement Learning with Verifiable Rewards (RLVR) to penalize incorrect logic and promote adaptive logic. The approach includes extracting problem‑solving logic, executing code to verify answers, and applying sanity checks, resulting in significant gains in mathematical reasoning performance and improved data efficiency.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.