Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.18842 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911430108774400 |
|---|---|
| author | Awad, Mohammad Nour Al Ivanov, Sergey Tikhonova, Olga |
| author_facet | Awad, Mohammad Nour Al Ivanov, Sergey Tikhonova, Olga |
| contents | Large Language Models (LLMs) have transformed code auto-completion by generating context-aware suggestions. Yet, deciding when to present these suggestions remains underexplored, often leading to interruptions or wasted inference calls. We propose an adaptive timing mechanism that dynamically adjusts the delay before offering a suggestion based on real-time developer feedback. Our suggested method combines a logistic transform of recent acceptance rates with a bounded delay range, anchored by a high-level binary prediction of the developer's cognitive state. In a two-month deployment with professional developers, our system improved suggestion acceptance from 4.9% with no delay to 15.4% with static delays, and to 18.6% with adaptive timing-while reducing blind rejections (rejections without being read) from 8.3% to 0.36%. Together, these improvements increase acceptance and substantially reduce wasted inference calls by 75%, making LLM-based code assistants more efficient and cost-effective in practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18842 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing LLM Code Suggestions: Feedback-Driven Timing with Lightweight State Bounds Awad, Mohammad Nour Al Ivanov, Sergey Tikhonova, Olga Software Engineering Artificial Intelligence Human-Computer Interaction Large Language Models (LLMs) have transformed code auto-completion by generating context-aware suggestions. Yet, deciding when to present these suggestions remains underexplored, often leading to interruptions or wasted inference calls. We propose an adaptive timing mechanism that dynamically adjusts the delay before offering a suggestion based on real-time developer feedback. Our suggested method combines a logistic transform of recent acceptance rates with a bounded delay range, anchored by a high-level binary prediction of the developer's cognitive state. In a two-month deployment with professional developers, our system improved suggestion acceptance from 4.9% with no delay to 15.4% with static delays, and to 18.6% with adaptive timing-while reducing blind rejections (rejections without being read) from 8.3% to 0.36%. Together, these improvements increase acceptance and substantially reduce wasted inference calls by 75%, making LLM-based code assistants more efficient and cost-effective in practice. |
| title | Optimizing LLM Code Suggestions: Feedback-Driven Timing with Lightweight State Bounds |
| topic | Software Engineering Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2511.18842 |