Science is changing independent of AI

Number of Researchers are Growing

International R&D spending

PhD Researchers

Intellectual bottlenecks are growing

📝 Increasing paper count ($\approx$15M per year)

🧬 Larger data sets from cheaper experiments (genome at $200 per person, $1 / GB of sequencing)

🔍95% decline in disruptive papers since 1980

AI Progress

Model intelligence doubles every ~4 months

Effect is Visible in Economy

What about in science?

Labbench 2

1,912 questions across accessing data, reading patents, reading figures, protocol understanding, etc.

Example: Deletion of which residues from C. elegans protein COSA-1 would most likely affect the ability of COSA-1 to recruit MSH5 and ZHP3?

Residues 31–40

Labbench 2 Accuracy

FutureHouse Timeline

Edison Scientific

• Spinout from FutureHouse formed in 2025
• AIxBio Research Lab that partners with biotech and pharma
• 50 employees
• $70M in seed financing

Introduction to AI Agents

How are agents trained?

1. Pre-training — broad knowledge via next-token prediction
2. Supervised Fine-Tuning (SFT) — learn from expert instruction–response pairs
3. Reinforcement Learning (RL) — optimize through environment interaction with verifiable rewards

RL expands capabilities beyond what supervised data can teach

Verifiable Rewards

Computational checks (code execution, tool outputs) produce objective reward signals — no human feedback needed

LabBench2: verifiable tasks as RL training signal

Behavior Changes

Training Curve

FutureHouse Agents

Automating research of scientific literature

Measurement: LAB-Bench (2024)

Approximately what percentage of Drosophila with a H3.3K36R mutation finish developing and enclose?

1. 80%
2. 19%
3. 50%
4. 37%
5. 6%
6. 94%

Better at answering questions than PhD biology experts

Improving over time

Better than human written Wikipedia articles

Edison Literature (PaperQA3)

Added patents, clinical trials, opentargets, chinese-language preprints. Designed for scientists

1. Provenance of claims
2. All actions auditable
3. Reproducible

PaperQA3 (2026)

Complete cycle of disease to target to drug

Robin proposes follow-up experiments

Robin optimizes the therapeutic candidates

Kosmos: An AI Scientist for Autonomous Discovery

Scientific Reasoning Models

Improving Models

Reasoning scaling

Can we build scientific reasoning models?

chemistry reasoning model

Works with molecular structures, but reasons in English

Start from base LLM and teach it chemistry

What can a reasoning model do?

Q:Propose a 1-step synthesis path that uses only commercially available reagents

Q: Propose a modification to this molecule to increase its solubility by about 1 LogS unit without affecting its scaffold.

data

Training Stages

Results vs humans and frontier models

State of Agents in 2026

Tool-State Paradox

$T_1=$ alphafold2
$T_2=$ $\beta$-sheet percentage

$T_2\rightarrow$ error, no pdb
$T_1,T_2\rightarrow$ success
$T_1,T_1,T_2\rightarrow$ need to treat multiple structures

Engineers must consider $O(2^{N})$ interactions between tools: will not scale past ~10 tools

Code-writing agents

LLMs manage state, you must only write good code

Challenges:

1. Must create persistent sandboxed computers for agents
2. Must solve security and authentication for agents

Kosmos Agent

A persistent always-on colleague that has access to 80% of public data, our chemistry and literature agents, and world models of biology