mlsanityData to 7 Oct 2026

Line-Anchored Feedback Cuts Token Costs and Improves Correctness in AI Code Editing

arXiv 2607.12713 ↗First posted 14 Jul 2026cs.SE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 22 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

12 of 22 references.

References · 12

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  3. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  4. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  5. 2019Green AIcited by 620
  6. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 216
  7. 2023Power Hungry Processing: Watts Driving the Cost of AI Deployment?cited by 186
  8. 2022Practical Program Repair in the Era of Large Pre-trained Language Modelscited by 133
  9. 2022Automating Code Review Activities by Large-Scale Pre-trainingcited by 98
  10. 2023A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challengescited by 75
  11. 2022Using Pre-Trained Models to Boost Code Review Automationcited by 63
  12. 2024Artificial Intelligence Policy Framework for Institutionscited by 3

Built on by

Not cited yet.