AI RESEARCH

Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation

arXiv CS.AI

ArXi:2602.01187v2 Announce Type: replace-cross Large Language Model (LLM) based code generation is predominantly formulated as a strictly monotonic process, appending tokens linearly to an immutable prefix. This formulation contrasts to the cognitive process of programming, which is inherently interleaved with forward generation and on-the-fly revision. While prior works attempt to