# Feedback-Calibrated Protein Optimization with Batch-Aligned Tail Arbitration

arXiv: https://arxiv.org/abs/2609.37808 · HTML: https://mlsanity.com/paper/2609.37808/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [Improving Protein Optimization with Smoothed Fitness Landscapes](https://mlsanity.com/paper/2307.00494/) (2023)
- [Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space](https://mlsanity.com/paper/2405.18986/) (2024)
- [Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences](https://mlsanity.com/paper/2412.07763/) (2024)
- [Thompson Sampling via Fine-Tuning of LLMs](https://mlsanity.com/paper/2510.13328/) (2025)
- [Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein Design](https://mlsanity.com/paper/2409.18582/) (2024)
- [A Variational Perspective on Generative Protein Fitness Optimization](https://mlsanity.com/paper/2501.19200/) (2025)
- [ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods](https://mlsanity.com/paper/2505.22494/) (2025)
- [Robust Model-Based Optimization for Challenging Fitness Landscapes](https://mlsanity.com/paper/2305.13650/) (2023)

## Abstract (arXiv)

Protein optimization aims to discover high-fitness sequences under a limited experimental budget. Existing machine-learning methods use task-specific predictors, biological priors, or ranking-aware objectives to guide which variants are tested in the next experimental round. However, these methods cannot adapt to shifts in the reliability of predictive evidence as measurements accumulate and ensure the correct ranking of key high-fitness candidates. To address these challenges, we propose Batch-Aligned Tail Arbitration (BATA), which uses experimental feedback to adaptively combine prior-informed and task-specific rankings for next-batch selection, with calibration focused on the batch-aligned high-fitness region. Across measured GB1, PABP, and TrpB landscapes, BATA achieves the best mean task rank (1.67) in final best fitness after 480 measurements. Controlled comparisons further show task-dependent gains from high-fitness calibration and batch alignment. Our work introduces feedback-calibrated predictor arbitration, where experimental feedback dynamically determines how predictive evidence guides next-batch selection, opening a new direction for protein optimization.