Model Releases
Line-Anchored Feedback Cuts Token Costs and Improves Correctness in AI Code Editing
arXiv:2607.12713v1 Announce Type: cross Abstract: Generated tokens are a direct driver of the cost, latency, and energy of generative AI (GAI) code editing. We show the format of feedback is a lever o
arXiv:2607.12713v1 Announce Type: cross Abstract: Generated tokens are a direct driver of the cost, latency, and energy of generative AI (GAI) code editing. We show the format of feedback is a lever on all three. We compare two deliveries of the same requested changes: a holistic prompt (control) versus the structured, line-anchored export of FileMark (treatment). FileMark is a VSCodium extension for inline comments on any file. In a paired experiment line anchoring cut generated tokens by 22% (Claude Opus) and 58% (Claude Sonnet), reaching 24%-80% on files of 100 lines or more, with four of seven models generating significantly fewer tokens after multiple-testing correction. Correctness rose where models had headroom: +2.0 points pooled and +5 to +7 points for three of five local models. An exploratory experiment in which the harness, not the GAI model, applies function-level patches shows the correctness benefit grows further when the edit-application burden is lifted: local-model correctness on 100+ line files roughly triples under anchoring. Line-anchored feedback reduces what stronger models spend and improves what weaker models get right.
Related
- Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification
- Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing
- When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs
Source: arXiv cs.AI | 2026-07-15