# LLM-Driven Heuristic Frame-Level Quantization Parameter Adaptation for VVenC

arXiv: https://arxiv.org/abs/2606.20847 · HTML: https://mlsanity.com/paper/2606.20847/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 6 of 6)

- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [AutoML-GPT: Automatic Machine Learning with GPT](https://mlsanity.com/paper/2305.02499/) (2023)
- [Is ChatGPT the Ultimate Programming Assistant -- How far is it?](https://mlsanity.com/paper/2304.11938/) (2023)

## Built on by (most cited first, 1 of 1)

- [Can LLMs Design Video Coding Tools? A Case Study on Planar Mode](https://mlsanity.com/paper/2609.01535/) (2026)

## Abstract (arXiv)

Optimal frame-level quantization parameter (QP) allocation remains a persistent challenge in modern video encoders. The fixed-QP scheme widely adopted in practical systems is inherently content-agnostic, while classical Lagrangian rate-distortion optimization (RDO) methods often suffer from inaccurate multiplier settings. In this paper, we explore the use of large language models (LLMs) to automatically design RDO heuristics for frame-level QP adaptation. We construct a closed-loop evolutionary framework in which the LLM iteratively proposes RDO heuristics as algorithmic ideas with executable code, and these candidates are evaluated directly through encoding with the Fraunhofer Versatile Video Encoder (VVenC), where each heuristic acts as a scoring function that compares different QP choices based on the encoding statistics of past frames and current candidates. Experimental results across multiple test sets show that the evolved heuristic achieves promising rate-distortion improvements over both the fixed-QP scheme and the Lagrangian baseline. Further analysis reveals that the LLM can autonomously discover an adaptive heuristic that penalizes QP fluctuations via entropy-based terms, providing new insights into the design of RDO algorithms