Beyond Surface-Level Pattern Trap: LLM Agents for Faster and Smarter Cross-Architecture Code Migration

The problem of surface-level pattern mapping represents a critical yet underexplored failure mode in large language model (LLM) reasoning, and is particularly acute in cross-architecture code migration of highperformance libraries. On low-resource, lowlevel code, insufficient coverage in pretraining data often leads LLMs to rely on superficial name-or type-based correspondences, rather than principled refactorization and reasoning grounded in core functional semantics and architecture-specific optimization intents. This tendency severely hampers the effectiveness of LLMs in complex migration scenarios. To address these challenges, we propose FSCM, a multi-agent framework for cross-architecture migration. FSCM decouples complex implementation details through functional mining and code refactoring, guiding LLMs to focus on invariant semantic anchors across architectures. By mitigating surface-level pattern traps, FSCM improves both functional correctness and performance when targeting emerging architectures. Extensive experiments on the challenging real-world OpenCV library migration tasks demonstrate substantial improvements over state-of-the-art baselines, achieving up to 22% higher correctness rates over Copilot and 43.04× speedup on RISC-V platforms. Code and data are available at: https: //github.com/breezejh/FSCM .