Evo-Recursive Constraint Prompting: An Operator-Based Framework for Structured HumanLLM Interaction

Large language models (LLMs) exhibit strong generative and reasoning abilities, but their
performance during interactive use remains highly sensitive to underspecified instructions,
evolving user intent, and missing structural constraints. Although practitioners routinely
refine prompts over multiple iterations, these interaction patterns are typically ad hoc and
lack a formal framework that makes them reproducible or analyzable.
We present Evo-Recursive Constraint Prompting (ERCP), a structured methodology
that formalizes common iterative prompting behaviors into four operator classes: recursive
refinement, constraint tightening, contradiction probing, and problem mutation. ERCP provides
an operator-level view of how humans guide LLM reasoning across iterations, enabling
explicit tracking of constraint evolution and error correction.
Rather than introducing new reasoning capabilities, ERCP systematizes widely used but
informal humanLLM prompting practices into an explicit workflow supported by a mathematical
abstraction and an algorithmic template. Through controlled case studies across
reasoning and synthesis tasks, we show that formalizing these operations leads to more stable
and interpretable iterative reasoning compared with unconstrained prompt refinement.
ERCP offers a reproducible foundation for analyzing and improving structured human LLM
interaction.