Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier
This addresses the problem of scalable and efficient verification for complex LLM reasoning tasks, offering a domain-specific improvement.
The paper tackles the trade-off between accuracy and computational efficiency in LLM reasoning by introducing FlexiVe, a generative verifier that balances fast and slow thinking, and the Solve-Detect-Verify pipeline for inference-time scaling, achieving superior error detection on ProcessBench and outperforming baselines like self-consistency on mathematical reasoning benchmarks.
Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates this landscape by introducing its own challenging trade-off: sophisticated Generative Reward Models (GenRMs) can be computationally prohibitive if naively integrated with LLMs at test-time, while simpler, faster methods may lack reliability. To overcome these challenges, we introduce FlexiVe, a novel generative verifier that flexibly balances computational resources between rapid, reliable fast thinking and meticulous slow thinking using a Flexible Allocation of Verification Budget strategy. We further propose the Solve-Detect-Verify pipeline, an efficient inference-time scaling framework that intelligently integrates FlexiVe, proactively identifying solution completion points to trigger targeted verification and provide focused solver feedback. Experiments show FlexiVe achieves superior accuracy in pinpointing errors within reasoning traces on ProcessBench. Furthermore, on challenging mathematical reasoning benchmarks (AIME 2024, AIME 2025, and CNMO), our full approach outperforms baselines like self-consistency in reasoning accuracy and inference efficiency. Our system offers a scalable and effective solution to enhance LLM reasoning at test time.