paper-with-me

Papers

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

2026-07-14 · William Franz Lamberti 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.

📄 PDF Abstract BibTeX arXiv:2607.12713

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Overcoming Shortcut Learning in Graph Neural Networks through Active Explanation Guidance

2026-08-14 · Taraneh Younesian, Steve Azzolin, Antonio Longa, Francesco Ferrini 외 arxiv

Graph Neural Networks (GNNs) can solve prediction tasks by unintentionally exploiting shortcuts---that is, edges, nodes, and features that correlate with but are not causal for the prediction---which compromise their rel…

Active Learning

Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR

2026-05-29 · Ruina Hu, Chen Wang, Lai Wei, Jionghao Bai 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) improves vision-language models (VLMs) by optimizing outcome rewards derived from final answers. However, such outcome-only rewards do not tell the model which image …

Reinforcement LearningMultimodal ReasoningVisual Grounding

AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning

2026-07-08 · Kyuan Oh, Bumsoo Kim arxiv

Large vision-language models incur substantial inference costs because high-resolution inputs introduce thousands of visual tokens, many of which are redundant for a given query. Existing pruning methods often combine qu…

Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation

2026-06-09 · Wenhao Zhang arxiv

On-policy distillation (OPD) has demonstrated strong empirical gains in enhancing complex reasoning in LLMs by aligning a student model with a teacher's predictive distribution over the student's own trajectories. An eme…

TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes

2026-08-13 · Jie Li, Chenxin Jia, Jinliang Shen, Cunzhuang Liu 외 arxiv

In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU. Dispatchers balance token counts (EPLB, LPLB, UltraEP) or activated-expert counts (METRO), assuming expert time is linear in one. Measurem…