6 min read

Virtual embryos and computer-using agents

Virtual embryos and computer-using agents
Nº 01 · The Lede X Field report

Navigo aims at virtual embryo

Navigo aims at virtual embryo
Fig. IX · Filed 26 Jun 2026.

Navigo couples flow matching at the population level with RNA kinetics modeling at the molecular level, sketching the first concrete pass at an AI-powered virtual embryo from Xiaojie Qiu's group. Flow matching (a generative technique that learns trajectories between distributions rather than single endpoints) lets the model interpolate developmental states; the kinetics layer ties those states to mRNA production and decay. Resets the reference target for developmental-biology AI: virtual cells now have a virtual-embryo north star, and the field gets a concrete artifact to benchmark against instead of slideware.

Read the source

Gemini gains native computer use
Fig. IIX · Filed 26 Jun 2026.
Nº 02 X Field report

Gemini gains native computer use

Google DeepMind shipped Gemini 3.5 Flash with native computer use, letting developers build agents that see and act across browsers, mobile, and desktop without bolt-on screen-scraping layers. Raises the floor for agent platforms: GUI control becomes a base-model feature, not a separate vendor stack — which matters for lab software, ELNs, and instrument interfaces that never got proper APIs and still expect a human at the mouse.

Read more
DeepSeek Flash flips agent economics
Fig. IIIHacker News · Filed 26 Jun 2026.
Nº 03 Hacker News Agents · Infrastructure

DeepSeek Flash flips agent economics

DeepSeek Flash inverted the cost curve for browser agents, according to a writeup from rtrvr.ai running text-only plans against full multimodal stacks. The pitch: cheap, fast tokens make code-as-plan competitive with vision-heavy approaches. Collapses the per-task cost ceiling for high-volume agent workloads — including the literature-mining and database-trawling jobs biology runs at scale.

Read more
Also Filed · Four Briefs from the queue
Nº 04 bioRxiv Cell biology · Funding

LLMs formalize cell-type calls

NanoCellAnnotator structures expert cell-type annotation through LLMs, turning the hand-curated calls that anchor every scRNA-seq paper into a reproducible pipeline. Moves single-cell annotation from artisanal to auditable — narrows one of the loudest reproducibility gaps in single-cell biology.

Read
Nº 05 arXiv Agents · Infrastructure

Socratic agents probe physical systems

Socratic agents tackle autonomous discovery in high-dimensional physical systems, using question-driven loops to surface structure base agents miss. Advances the methodology of autonomous discovery itself — the same loop transfers to biophysics and high-dimensional omics, where the search space looks similar.

Read
Nº 06 arXiv Field report

Discovery as meta-optimization

A new arXiv paper frames scientific discovery as meta-optimization, using combinatorial optimization as the test case. Anchors a counterpoint to pure-LLM discovery pipelines: structured search still earns its keep, and the debate over how much reasoning belongs in the model versus the loop gets a concrete reference point.

Read
Nº 07 bioRxiv Field report

trAIt pulls species-trait data

trAIt retrieves species-by-trait data via LLMs, automating one of comparative biology's most tedious literature-extraction jobs. Closes a long-standing data-assembly bottleneck for trait-based ecology and evolutionary work.

Read

Reply with your discoveries. A human reads them. Forward freely.

Agentic Discovery  ·  Nº 44  ·  26 Jun 2026

Editor's Note

A virtual embryo, a computer-using Gemini, and DeepSeek Flash quietly flipping agent economics — Thursday earns its bandwidth.

 

Nº 01 · The Lede  —  X  —  Field report

Navigo aims at virtual embryo

Navigo aims at virtual embryo

Fig. I  X · Filed 26 Jun 2026.

Navigo couples flow matching at the population level with RNA kinetics modeling at the molecular level, sketching the first concrete pass at an AI-powered virtual embryo from Xiaojie Qiu's group. Flow matching (a generative technique that learns trajectories between distributions rather than single endpoints) lets the model interpolate developmental states; the kinetics layer ties those states to mRNA production and decay. Resets the reference target for developmental-biology AI: virtual cells now have a virtual-embryo north star, and the field gets a concrete artifact to benchmark against instead of slideware.

Read the source →

Why it matters

Moves whole-organism simulation from aspiration to working prototype — the cell-scale AI agenda now has an embryo-scale next rung, and funders with virtual-cell theses have a clear extension to underwrite.

 

Nº 02  —  X  —  Field report

Gemini gains native computer use

Fig. II  X · Filed 26 Jun 2026.

Gemini gains native computer use

Google DeepMind shipped Gemini 3.5 Flash with native computer use, letting developers build agents that see and act across browsers, mobile, and desktop without bolt-on screen-scraping layers. Raises the floor for agent platforms: GUI control becomes a base-model feature, not a separate vendor stack — which matters for lab software, ELNs, and instrument interfaces that never got proper APIs and still expect a human at the mouse.

Read more →

 

Nº 03  —  Hacker News  —  Agents · Infrastructure

DeepSeek Flash flips agent economics

Fig. III  Hacker News · Filed 26 Jun 2026.

DeepSeek Flash flips agent economics

DeepSeek Flash inverted the cost curve for browser agents, according to a writeup from rtrvr.ai running text-only plans against full multimodal stacks. The pitch: cheap, fast tokens make code-as-plan competitive with vision-heavy approaches. Collapses the per-task cost ceiling for high-volume agent workloads — including the literature-mining and database-trawling jobs biology runs at scale.

Read more →

 

Also Filed  ·  Four Briefs from the queue

Nº 04  —  bioRxiv  —  Cell biology · Funding

LLMs formalize cell-type calls

NanoCellAnnotator structures expert cell-type annotation through LLMs, turning the hand-curated calls that anchor every scRNA-seq paper into a reproducible pipeline. Moves single-cell annotation from artisanal to auditable — narrows one of the loudest reproducibility gaps in single-cell biology.

Read →

Nº 05  —  arXiv  —  Agents · Infrastructure

Socratic agents probe physical systems

Socratic agents tackle autonomous discovery in high-dimensional physical systems, using question-driven loops to surface structure base agents miss. Advances the methodology of autonomous discovery itself — the same loop transfers to biophysics and high-dimensional omics, where the search space looks similar.

Read →

Nº 06  —  arXiv  —  Field report

Discovery as meta-optimization

A new arXiv paper frames scientific discovery as meta-optimization, using combinatorial optimization as the test case. Anchors a counterpoint to pure-LLM discovery pipelines: structured search still earns its keep, and the debate over how much reasoning belongs in the model versus the loop gets a concrete reference point.

Read →

Nº 07  —  bioRxiv  —  Field report

trAIt pulls species-trait data

trAIt retrieves species-by-trait data via LLMs, automating one of comparative biology's most tedious literature-extraction jobs. Closes a long-standing data-assembly bottleneck for trait-based ecology and evolutionary work.

Read →

 

· · ·

Reply with your discoveries. A human reads them. Forward freely.