{"version":1,"type":"story","url":"https://digestai.news/story/google-research-builds-ai-agents-for-autonomous-wet-lab-experiments","json":"https://digestai.news/story/google-research-builds-ai-agents-for-autonomous-wet-lab-experiments.json","markdown":"https://digestai.news/story/google-research-builds-ai-agents-for-autonomous-wet-lab-experiments.md","slug":"google-research-builds-ai-agents-for-autonomous-wet-lab-experiments","headline":"Google Research builds AI agents for autonomous wet-lab experiments","summary":"Google Research has detailed three projects aimed at integrating AI agents with physical laboratory robotics to automate biological discovery. The core challenge is that current frontier models struggle with 3D geometry and physical state, making them unreliable for controlling liquid-handling robots. To address this, the team developed VERID, a semantic digital twin that tracks the live physical context of the lab, including robotic arm positions and reagent volumes, to prevent physically impossible or unsafe commands.\n\nIn one study, AI agents used VERID to run closed-loop experiments, recovering from hardware failures and refining mixing strategies based on video feedback. In another, agents designed DNA aptamers in a 7–10 day cycle, raising on-target hit rates to 33.5% for myoglobin and 42.1% for α-thrombin after learning to avoid non-specific binding artifacts. The agents autonomously revised their design rules when initial strategies failed, demonstrating a capacity for scientific reasoning and self-correction.\n\nFor protein design, the team applied this workflow to fibroblast activation protein alpha (FAP), a cancer target. By using a technique called epitope excision to reduce computational load, they accelerated the design cycle more than eightfold. Human-agent collaboration nearly doubled the in-silico hit rate compared to human-only work, yielding binders with single-digit nanomolar affinity. These efforts form a foundation for human-directed autonomous discovery in the life sciences.","keyPoints":["VERID framework creates a digital twin to ground AI agents in physical lab reality.","AI agents raised aptamer hit rates to 33.5% and 42.1% in closed-loop cycles.","Agent-guided protein design found single-digit nanomolar binders for cancer targets."],"whyItMatters":"This research bridges the gap between computational AI and physical experimentation, enabling faster, automated drug discovery. It addresses a key bottleneck in biology by allowing AI to safely operate lab robots and learn from real-world feedback.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["Google Research"],"models":["VERID"],"people":["Pooja Rao","Petar Sirkovic","Annalisa Pawlosky"]},"firstPublishedAt":"2026-10-16T18:11:34Z","updatedAt":"2026-10-16T18:11:34Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"Google Research","title":"Grounding AI agents in biological reality: Building blocks for autonomous wet labs","url":"https://research.google/blog/grounding-ai-agents-in-biological-reality-building-blocks-for-autonomous-wet-labs","publishedAt":"2026-10-16T18:11:34Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Google Research builds AI agents for autonomous wet-lab experiments\", 16 October 2026, https://digestai.news/story/google-research-builds-ai-agents-for-autonomous-wet-lab-experiments","publisher":"Digest AI","title":"Google Research builds AI agents for autonomous wet-lab experiments","datePublished":"2026-10-16T18:11:34Z","url":"https://digestai.news/story/google-research-builds-ai-agents-for-autonomous-wet-lab-experiments"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}