AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
cs.AI
Submitted: 2026-05-27
Updated: 2026-11-10
Code: https://github.com/mims-harvard/AutoScientists
Project page: https://autoscientists.openscientist.ai
License: http://creativecommons.org/licenses/by/4.0/
The gist: Scientific research proceeds through iterative cycles of hypothesis generation, experiment design, execution, and revision.
Terminology
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).
Sources
- Kosmos: An AI Scientist for Autonomous Discovery
- TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools
- Accelerating scientific discovery with Co-Scientist
- AIDE: AI-Driven Exploration in the Space of Code
- CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
- InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
- ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
- Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions
- A Vision for Auto Research with LLM Agents
- LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research
- Robin: A multi-agent system for automating scientific discovery
- GenoMAS: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data
- PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration
- ChemBOMAS: Accelerated BO in Chemistry with LLM-Enhanced Multi-Agent System
- SR-Scientist: Scientific Equation Discovery With Agentic AI
- SelfAI: A self-directed framework for long-horizon scientific discovery
- EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery
- CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Language Agents as Optimizable Graphs
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents