Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics

The paper addresses the failure of large language models (LLMs) in code generation when routine correctness relies on execution-dependent coupling—situations where the meaning of one routine depends on another’s runtime behavior. It introduces a dynamic context adaptation framework that iteratively validates generated code, extracts diagnostic information from execution traces, and guides generation using a knowledge graph and simulated annealing. Experiments show the method surpasses zero‑shot, Reflexion, and OpenEvolve on most benchmark problems, especially where runtime coupling is critical.

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.

• llms
• agents
• benchmarks