# Leveraging generative hallucination and biophysics-informed modeling for unified biomolecular sequence-structure co-design

arXiv: https://arxiv.org/abs/2608.17381 · HTML: https://mlsanity.com/paper/2608.17381/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 41 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 7 of 7)

- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [gRNAde: Geometric Deep Learning for 3D RNA inverse design](https://mlsanity.com/paper/2305.14749/) (2023)
- [Entropy-Reinforced Planning with Large Language Models for Drug Discovery](https://mlsanity.com/paper/2406.07025/) (2024)
- [ControllableGPT: A Ground-Up Designed Controllable GPT for Molecule Optimization](https://mlsanity.com/paper/2502.10631/) (2025)
- [ScaffoldGPT: A Scaffold-based GPT Model for Drug Optimization](https://mlsanity.com/paper/2502.06891/) (2025)
- [Monte Carlo Tree Diffusion with Multiple Experts for Protein Design](https://mlsanity.com/paper/2509.15796/) (2025)
- [FragmentGPT: A Unified GPT Model for Fragment Growing, Linking, and Merging in Molecular Design](https://mlsanity.com/paper/2509.11044/) (2025)

## Abstract (arXiv)

Biomolecular design underpins applications from molecular recognition to therapeutics and synthetic biology, yet de novo interaction design remains challenging-especially for DNA/RNA, underexplored non-protein modalities with scarce, heterogeneous complex data and sharper geometric and chemical constraints. We introduce MCTH (Monte Carlo Tree Hallucination), an inference-only framework that casts all-atom sequence-structure co-design as uncertainty-aware planning over hallucinated states from pretrained folding and inverse-folding models, with optional biophysical control within the same decision loop. MCTH treats these models as frozen black-box operators and uses Monte Carlo Tree Search to allocate a fixed inference budget across competing design trajectories, incorporating model confidence and uncertainty, as well as cross-expert consensus/disagreement when multiple predictors are available. Across protein-RNA, protein-DNA, protein-protein, and protein-ligand design, matched-budget experiments show that adaptive search improves over simpler sampling and cycling strategies, while held-out AlphaFold3 and Chai-1 evaluations demonstrate transfer beyond the search-time oracle. MCTH provides a shared planning layer across modalities while allowing task-specific folding, inverse-folding, and biophysical modules, requiring no fine-tuning or backpropagation through component models.