AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
- URL: http://arxiv.org/abs/2605.28655v1
- Date: Wed, 27 May 2026 15:56:12 GMT
- Title: AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
- Abstract summary: AutoScientists is a decentralized team of AI agents for long-running computational scientific experimentation.<n>Agents interpret a shared experimental state, self-organize into teams around promising hypotheses, critique proposals before using experimental compute.<n>Under matched experimental budgets, AutoScientists improves over prior AI agents across biomedical machine learning, language-model training optimization, and protein fitness prediction.
- Score: 28.790523063833376
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Scientific research proceeds through iterative cycles of hypothesis generation, experiment design, execution, and revision. AI agents can automate parts of this process, but existing approaches typically follow a single research trajectory or coordinate through a central planner with fixed objectives. As a result, they struggle to sustain parallel exploration, adapt as experimental evidence changes, or preserve knowledge of failed directions over long-running experiments. We introduce AutoScientists, a decentralized team of AI agents for long-running computational scientific experimentation. Agents interpret a shared experimental state, self-organize into teams around promising hypotheses, critique proposals before using experimental compute, and share successes and failures to reduce redundant exploration. Under matched experimental budgets, AutoScientists improves over prior AI agents across biomedical machine learning, language-model training optimization, and protein fitness prediction. On BioML-Bench, spanning biomedical imaging, protein engineering, single-cell omics, and drug discovery, AutoScientists achieves a mean leaderboard percentile of 74.4% across 24 tasks, improving over the strongest AI agent by +8.33%. On GPT training optimization, AutoScientists reaches a target validation bits-per-byte 1.9x faster than Autoresearch and continues discovering improvements from a starting champion where the single-agent approach finds none (7 vs. 0 accepted improvements). On ProteinGym fitness prediction, AutoScientists discovers a method for ACE2-Spike binding that improves over the current state-of-the-art model by +12.5% in Spearman correlation. Applied without modification across all 217 ProteinGym assays, the same method improves over the prior state of the art by +6.5% (Spearman correlation).
Related papers
- LabAgent: Customize Any Research Hubs for Scientific Discoveries Using AI Agents [54.20891951945591]
Methods developed by predecessors are often expanded upon by new researchers to explore more novel and in-depth scientific questions.<n>The change of lab staff, such as student graduation, leads to a lack of personnel capable of replicating methods.<n>We propose LabAgent, a reproduce and discovery harness tailored for a lab's continuous work.
arXiv Detail & Related papers (2026-09-11T18:53:18Z) - Towards Automating Scientific Review with Google's Paper Assistant Tool [43.64244794415017]
Paper Assistant Tool (PAT) is an agentic AI framework built for deep scientific review and verification.<n>Pilot deployments of PAT as a pre-submission tool for authors at two major Computer Science conferences demonstrate its ability to identify critical errors.<n> PAT eases the cognitive burden placed on referees, while preserving their control over the outcomes of the review process.
arXiv Detail & Related papers (2026-06-26T17:19:17Z) - Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery [51.70607714288616]
Science Earth is a planet-scale scientific runtime in which any capability can connect to any other.<n>Its underlying EACN protocol lets capabilities discover one another, negotiate task ownership, and adjudicate across incompatible evidentiary standards.<n>Two runs validate this under structurally distinct conditions.
arXiv Detail & Related papers (2026-05-31T16:05:41Z) - AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration [175.74514061083195]
We present AutoResearchClaw, a multi-agent autonomous research pipeline built on five mechanisms.<n>On ARC-Bench, a 25-topic experiment-stage benchmark, AutoResearchClaw outperforms AI Scientist v2 by 54.7%.
arXiv Detail & Related papers (2026-05-19T15:49:51Z) - AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite [75.58737079136942]
We present AstaBench, a suite that provides the first holistic measure of agentic ability to perform scientific research.<n>Our suite comes with the first scientific research environment with production-grade search tools.<n>Our evaluation of 57 agents across 22 agent classes reveals several interesting findings.
arXiv Detail & Related papers (2025-10-24T17:10:26Z) - InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification [24.752098402554743]
InternAgent is a unified closed-loop multi-agent framework to conduct Autonomous Scientific Research.<n>It has demonstrated its versatility across 12 scientific research tasks.<n>It has achieved promising performance gains in several scientific fields with significantly less time cost compared to human efforts.
arXiv Detail & Related papers (2025-05-22T17:27:43Z) - Towards an AI co-scientist [48.11351101913404]
We introduce an AI co-scientist, a multi-agent system built on Gemini 2.0.<n>The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses.<n>The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method.
arXiv Detail & Related papers (2025-02-26T06:17:13Z) - BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments [112.25067497985447]
We introduce BioDiscoveryAgent, an agent that designs new experiments, reasons about their outcomes, and efficiently navigates the hypothesis space to reach desired solutions.<n>BioDiscoveryAgent can uniquely design new experiments without the need to train a machine learning model.<n>It achieves an average of 21% improvement in predicting relevant genetic perturbations across six datasets.
arXiv Detail & Related papers (2024-05-27T19:57:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.