arXiv AI August 28, 2026 By Mingquan Liu, Jiangyu Chen, Hanqun Cao, Xujun Zhang, Pengsen Ma, Xiangru Tang, Shuting Jin, Zhuo Yang, Tianfan Fu, Fang Wu, Xiangxiang Zeng

AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design

Read the original on arXiv AI →

AgentFold is a multi‑agent framework that treats protein‑folding model design as a closed‑loop search over executable code variants. Starting from the ESMFold codebase, the agents generate hypotheses, modify and debug code, evaluate model variants, and store both successes and failures in structured memory, guided by an MCTS‑style policy that allocates GPU resources. In an engineering‑scale experiment, AgentFold explored about 80 variants using 5,000 GPU‑hours and 170 million LLM tokens, improving the best lDDT score by 7.5% over independent Codex proposals and outperforming a random‑search baseline, while also uncovering empirical design patterns such as the benefits of early, soft, learnable priors.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Oct 15

ReproBAIT: Can coding agents build their own biological AI tools?

arXiv:2610.19810v1 Announce Type: cross Abstract: Large language models are increasingly competent at leveraging scientific knowledge and existing computational tools to execute complex workflows. At...

By Shiv Muthupandiyan, Tolga H. Dur, Mac Walker, Timo Flesch, Mahmoud Ghanem, Steph Suddell, Giles Harper-Donnelly, Sophie Rose, Jasper G\"otting, Coleman Breen, Jake Pencharz

llms agents diffusion

arXiv AI

Jun 16

Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

arXiv:2603. 15952v2 Announce Type: replace Abstract: Large language models (LLMs) are capable of emulating reasoning and using tools, creating opportunities for autonomous agents that execute complex scientific tasks.

By Jacopo Teneggi, S. M. Bargeen A. Turzo, Tanya Marwah, Alberto Bietti, P. Douglas Renfrew, Vikram Khipple Mulligan, Siavash Golkar

llms agents

arXiv Machine Learning

Aug 21

ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning

arXiv:2506. 07459v4 Announce Type: replace Abstract: Protein generative models have shown remarkable promise in protein design, yet their success rates remain constrained by reliance on curated sequence-structure datasets and by misalignment between supervised objectives and real design goals.

By Ziwen Wang, Jiajun Fan, Ruihan Guo, Thao Nguyen, Heng Ji, Ge Liu

rag reinforcement-learning fine-tuning benchmarks

arXiv AI

Aug 3

AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers

arXiv:2607. 29626v1 Announce Type: new Abstract: As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important.

By Tianyu Huai, Tingshuo Fan, Xinchi Chen, Yining Zheng, Yuxin Wang, Shuang Chen, Jie Zhou, Xuanjing Huang

llms agents benchmarks

arXiv Computation and Language

Sep 2

Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops

The paper investigates code-level autonomous research loops (ARLs) where a language model edits training pipelines to improve an in-loop metric. It identifies a failure mode called algorithmic mode collapse, where edits become semantically uniform despite surface diversity, leading to a growing gap between in-loop gains and independent evaluation. The authors propose Diversity‑Aware Proposal Sampling (DAPS), a lightweight method that reduces semantic decay by 69.1% and boosts faithfulness by over 80% while maintaining optimization speed.

By Bowei He, Weixu Zhang, Yili Jin, Xue Liu

llms agents

arXiv AI

Sep 10

Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools

arXiv:2609.05818v1 Announce Type: new Abstract: We introduce ABLE, a benchmark for evaluating LLM agents' ability to use biological AI models (BAIMs), such as ProteinMPNN and AlphaFold3, in dual-use...

By Bryce Cai, Geetha Jeyapragasan, Samira Nedungadi, Jake Yukich, Seth Donoughe

llms agents benchmarks

One email a morning, machine-written

Related stories

ReproBAIT: Can coding agents build their own biological AI tools?

Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning

AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers

Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops

Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools