arXiv Machine Learning
ReproBAIT: Can coding agents build their own biological AI tools?
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 28
AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design
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.
arXiv AI
Sep 16
Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance
arXiv:2609.16213v1 Announce Type: new Abstract: Artificial intelligence is reshaping biological research across an increasingly connected digital-to-physical workflow. General-purpose large language...
arXiv AI
Aug 11
ToolUniverse: An open platform for democratizing AI scientists
arXiv:2509. 23426v3 Announce Type: replace Abstract: AI scientists are emerging computational systems that serve as collaborative partners in discovery.
arXiv AI
Jun 10
ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity
arXiv:2606. 11150v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly acquiring capabilities relevant to biological research, from literature synthesis to interpretation of experimental data.
arXiv AI
Jun 11
Can AI Agents Synthesize Scientific Conclusions?
arXiv:2606. 11337v1 Announce Type: new Abstract: Scientific AI agents increasingly retrieve evidence, reason across sources, and synthesize conclusions used in consequential decisions.
arXiv AI
Sep 3
Can Coding Agents Reproduce Findings in Computational Materials Science?
The paper introduces AutoMat, a benchmark designed to test large language model (LLM) coding agents on their ability to reproduce claims from computational materials science. AutoMat presents three challenges: reconstructing underspecified procedures, navigating specialized toolchains, and assessing whether the evidence supports a claim. Experiments show that current LLM agents achieve low success rates, with the best setting reaching only 53%, and failures stem mainly from incomplete procedures, methodological deviations, and execution fragility.