# Optimizing LLM Code Suggestions: Feedback-Driven Timing with Lightweight State Bounds

arXiv: https://arxiv.org/abs/2511.18842 · HTML: https://mlsanity.com/paper/2511.18842/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules](https://mlsanity.com/paper/2310.08992/) (2023)
- [Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support](https://mlsanity.com/paper/2502.18658/) (2025)
- [When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming](https://mlsanity.com/paper/2306.04930/) (2023)
- [Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases](https://mlsanity.com/paper/2308.09313/) (2023)
- [ComplexCodeEval: A Benchmark for Evaluating Large Code Models on More Complex Code](https://mlsanity.com/paper/2409.10280/) (2024)
- [When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference](https://mlsanity.com/paper/2401.09964/) (2024)
- [A Systematic Evaluation of Large Code Models in API Suggestion: When, Which, and How](https://mlsanity.com/paper/2409.13178/) (2024)
- [A Transformer-Based Approach for Smart Invocation of Automatic Code Completion](https://mlsanity.com/paper/2405.14753/) (2024)
- [Understanding User Mental Models in AI-Driven Code Completion Tools: Insights from an Elicitation Study](https://mlsanity.com/paper/2502.02194/) (2025)

## Built on by (most cited first, 2 of 2)

- [Agentic Coding Needs Proactivity, Not Just Autonomy](https://mlsanity.com/paper/2605.06717/) (2026)
- [Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair](https://mlsanity.com/paper/2606.30963/) (2026)

## Abstract (arXiv)

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.