---
title: "TTS-Design: Test-Time Compute Scaling for Structure-Guided Protein Design"
authors:
  - "Zizhe Jin"
  - "Yizhen Zheng"
  - "Huan Yee Koh"
  - "Jiaxin Ju"
  - "Jiapu Wang"
  - "Shirui Pan"
doi: "10.24963/ijcai.2026/616"
url: "https://ijcai.org/proceedings/2026/616"
pdf: "https://ijcai.org/proceedings/2026/0616.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "5531-5539"
track: "Main Track"
keywords:
  - "Machine Learning: Sequence and graph learning"
  - "Multidisciplinary Topics and Applications: Bioinformatics"
  - "AI: Machine Learning"
  - "Multidisciplinary Topics and Applications: Health and medicine"
---

# TTS-Design: Test-Time Compute Scaling for Structure-Guided Protein Design

Zizhe Jin, Yizhen Zheng, Huan Yee Koh, Jiaxin Ju, Jiapu Wang, Shirui Pan

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 5531-5539. DOI: [10.24963/ijcai.2026/616](https://doi.org/10.24963/ijcai.2026/616)

## Abstract

Generating protein sequences that reliably fold into target structures is a central challenge in computational biology and protein design. Progress in protein inverse folding (PIF), however, is fundamentally constrained by the scarcity of high-quality structural data, which limits the effectiveness of existing models. In this work, we propose TTS-Design, a test-time compute scaling framework that enhances protein sequence design without retraining models or relying on larger training data. For TTS-Design, its core design is a dedicated inverse folding reward model named IF-RM, which quantitatively evaluates structure–sequence compatibility and enables effective selection among multiple candidate sequences at inference time. By integrating IF-RM into existing PIF models, TTS-Design leverages additional computation during inference stage to explore and refine candidate solutions. Extensive experiments on the CATH 4.2 and CATH 4.3 demonstrate that TTS-Design consistently improves sequence recovery and structural reliability across different backbone models, without retraining or increasing model size. Case studies on real-world proteins further confirm its practical effectiveness. Overall, our results highlight test-time compute scaling as a promising and effective paradigm for advancing protein inverse folding and other scientific problems under data-limited scenarios.