Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs

Excerpt

arXiv:2609.28150v1 Announce Type: new Abstract: Closed-loop revision is increasingly used in large language model (LLM) applications, but failures may reflect incomplete feedback or ineffective responses to correct feedback. We introduce a fixed-budget revision protocol with deterministic verifiers that report all remaining violations across exact-length, lexical, and compositional constraints. Fixing feedback correctness and completeness isolates model-side revision behavior. Across 19 open- an