AI for Bio · Model

Robin

FutureHouse multi-agent discovery system linking literature review, candidate proposal and data analysis

Text, LLMs & agentsNonprofit instituteUnited StatesActive中文

Overview

NameRobin
Full nameNo separate expanded name
Ambiguous names (not auto-linked)Robin
FamilyNot a family entry. Single-model entry, not a family
OrganizationFutureHouse
Organization typeNonprofit institute
CountryUnited States
Model classMulti-agent discovery system
DomainText, LLMs & agents
First release · preprint
Basis: arXiv 2505.13400 v1 submitted source
Other milestones
  • Preprint v1: · arXiv v1 source
  • Journal online: · Nature publication source
Latest update · journal
Basis: Nature journal publication
Paper published in Nature source
The most recent sourced event, not a claim that nothing changed since.
StatusActive · Journal publication within 12 months
OpennessCode: Open
Weights: Unclear
Code released, but running it needs a FutureHouse platform key
Benchmarks reported0 counted · none of the 44
Wet-lab validation1 recorded campaign
Unverified fieldsNone
As of2026-11-16

What it does

Three agents (Crow, Falcon, Finch) handle literature review, candidate proposal and experimental data analysis; demonstrated on dry age-related macular degeneration, with proposed candidates tested in the wet lab.

Benchmarks reported

None of the 44 benchmarks. This model is on the zero-pairing list.

How it evaluates itself: Dry AMD lab-in-the-loop; Effect size conflict

Other evaluations (outside the 44)

  • Dry-AMD lab-in-the-loop (Wet-lab validation) Self-reported: Two rounds of cell assays: 5 of 30 candidates, then 10
  • Effect size conflict (Case study) Self-reported: Same effect: agent analysis 7.5x, human 1.75x; authors call for more testing

Developers report: Developers report the first multi-agent system to autonomously hypothesize, plan, analyze and propose a validated new candidate

Independent evidence: No independent evidence found. No independent evidence found

Training data

Group in Figure 7: Public data + wet lab for validation only.

ClassValueDetail
a. Public databasesYesBase model and retrieval tools use public literature
b. Private or licensed dataNot disclosed
c. Own wet-lab data used for trainingNo
d. Wet lab used only for validationYesCell phagocytosis assays tested candidates source

Wet-lab validation

Every rate carries its numerator and denominator. Claims that could not be verified are shown as unverified, without numbers; different paper versions are separate entries.

Dry-AMD lab-in-the-loop (two rounds) (paper)
Targets — · Designs tested 10 · Hits — · Success — · Best affinity —

Denominator basis: Round 1 tested 5 of 30 proposed candidates, round 2 tested 10; no hit rate reported
Team-run experiments and analysis, not independent; agent and human estimates of the same effect differ (7.5x vs 1.75x); authors call for more dose/time testing

Self-reported · No sourced date · verified · source

Background

  • Organization: FutureHouse is a nonprofit AI-science lab founded in San Francisco in 2023-09; its commercial arm is Edison Scientific
  • Funding: Not disclosed or not applicable
  • Products and partnerships: Done with Oxford collaborators; related products Kosmos and Finch
  • Related models: Kosmos / Edison Analysis, Biomni

Reading notes

  1. Wet-lab work is small and team-run: a demonstration
  2. Agent and human effect sizes differ about 4-fold; both should be shown

Caveats

  1. No results reported on any of the 44 benchmarks
  2. Round-2 hit outcomes not reported

Sources

  1. Crossref record 10.1038/s41586-026-10652-y (journal)
  2. Official page futurehouse.org (company blog)
  3. arXiv preprint 2505.13400 (preprint)
  4. Journal or proceedings page (journal)

Corrections

None recorded.

Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.