Decentralized multi-agent LLM framework where agents self-organize into teams for long-running computational research.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
AutoScientists is a research framework from Shanghua Gao, Ada Fang and Marinka Zitnik. It deploys several long-running LLM agents with no central orchestrator. The agents read a shared experimental state, form teams around research directions, and run experiments in parallel. The shared state holds the current champion program, an experiment log, a structured discussion forum, and per-team queues and dead-end registries that other teams can read.
The system alternates between a discussion phase and an execution phase. In discussion, agents critique and filter proposals before any experimental compute is committed. When a team stagnates, agents trigger re-discussion and may reorganize into new teams. Both successful and failed findings are shared across teams to reduce redundant exploration. Analyst agents handle proposal generation, knowledge-file maintenance and hypothesis tracking.
According to the project page, at matched experimental budgets it reaches a mean leaderboard percentile of 74.4% across the 24 BioML-Bench tasks, against 66.07% for autoresearch. On GPT (nanochat) training optimization it reaches a target validation bits-per-byte 1.9x faster than autoresearch. On ProteinGym it found a Kermut-based method that improves average Spearman correlation from 0.657 to 0.700 across 217 assays. These are the authors' own reported results. The system targets computational experiments with automatically gradable outcomes, not wet-lab work.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Open-source multi-agent framework where agents act as a decentralized research lab with a shared state, experiment log, forum and dead-end registry. Beats other agentic frameworks on BioML-bench's 24 biomedical ML tasks.
Closest neighbours by meaning, not just by category.
Agent · Google DeepMind
Gemini-based multi-agent system from Google that generates, debates and ranks scientific hypotheses for researchers.
Model
35B Mixture-of-Experts open-weights model from InternScience for long-horizon agentic search, engineering and tool use.
Research
Open-source repo where an AI agent autonomously edits and runs 5-minute nanochat LLM training experiments on one GPU.
Research · OpenAI
OpenAI and Molecule.one research system pairing GPT-5.4 with the Maria agentic chemistry platform and a high-throughput lab.
Research · Meta
Meta research framework where an AI agent acts as a data scientist, iteratively building training and evaluation datasets.
Model · Alpha Innovator
35B mixture-of-experts open-weights agentic model for engineering, long-horizon search and scientific research.