# Preprint reports agent system improved protein-folding model search under matched compute

_Friday, August 28, 2026 at 12:00 AM EDT · Science, AI · Latest · Tier 2 — Notable_

An arXiv preprint describes AgentFold, a multi-agent system that modifies and evaluates protein-folding model code in a closed-loop search. Starting from ESMFold, the researchers say it explored about 80 variants, consuming about 5,000 GPU-hours and 170 million LLM tokens. Under a matched compute budget, it improved the best lDDT by 7.5% over independent Codex proposals and beat a random-search control. Code and experimental resources are publicly available.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2608.26747)

---
Canonical: https://techandbusiness.org/newswire/5nY1D8kBOdvk-OxNjCN7V8
Retrieved: 2026-08-28T12:43:36.643Z
Publisher: Tech & Business (techandbusiness.org)