5 min read

From advice to dosing decisions

From advice to dosing decisions
Nº 01 · The Lede arXiv Agents · Infrastructure

DiabAgent aims AI agents at blood-glucose control

DiabAgent aims AI agents at blood-glucose control
Fig. IarXiv · Filed 03 Nov 2026.

DiabAgent puts a language-model agent (software that plans and acts over several steps on its own) inside a physiological control loop, treating blood-glucose management as a task the agent runs rather than a question it answers. Automated glucose control already exists in closed-loop insulin pumps, but those controllers follow fixed algorithms. The case for agentic control is that a reasoning system can weigh context a fixed controller never sees, including meals, activity, and how a patient responded last time. The 'toward' in the arXiv paper is honest. This is framing and early machinery, not a clinical result.

Read the source →

Research agent tunes alignments for complex prediction
Fig. IIarXiv · Filed 03 Nov 2026.
Nº 02 arXiv Agents · Infrastructure

Research agent tunes alignments for complex prediction

An agent runs its own research on multiple sequence alignments, searching for ways to organize and pair them that improve predicted structures of protein-protein complexes. Alignment construction is one of the few levers left in complex prediction, and groups have tuned it by hand for years. In this arXiv work the tuning is the agent's job: it proposes alignment strategies and evaluates them against prediction accuracy. Agents are starting to propose method changes, not only execute pipelines someone else designed.

Read more →
Single-cell model links expression and chromatin state
Fig. IIIbioRxiv · Filed 03 Nov 2026.
Nº 03 bioRxiv Cell biology · Funding

Single-cell model links expression and chromatin state

One model reads transcriptome and chromatin together, learning a shared representation across single-cell RNA and accessibility data so one modality can be analyzed in terms of the other. Most single-cell foundation models — general models trained broadly rather than built for one task — handle expression alone, leaving multiome data to separate integration tools. The bioRxiv preprint reports cross-modality analysis coming out of one pretrained model.

Read more →
Also Filed · Three Briefs from the queue
Nº 04 bioRxiv Structural biology · Protein design

Tuned protein models find dual-target peptides

Protein language models retuned cheaply pick out antimicrobial peptides active against two targets at once, with only a small fraction of model weights adjusted. Training and test sets were split under strict homology cutoffs, so near-identical sequences can't inflate the reported performance.

Read →
Nº 05 OpenAI Field report

Anima cuts clinic call waits by 75%

Clinic call waits dropped 75% at practices using Anima, which builds patient-facing tools on OpenAI's GPT-6 and GPT-Live, according to OpenAI's customer write-up. What changed is how quickly patients reach a clinic, not what the clinic decides.

Read →
Nº 06 OpenAI Agents · Infrastructure

OpenAI coordinates fixes as agents find critical bugs

Agents turned up critical vulnerabilities in open-source code, and OpenAI built Patch the Planet to route those findings to maintainers and incident responders ahead of disclosure. Much of the software research depends on is maintained by volunteers.

Read →

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

Agentic Discovery  ·  Nº 134  ·  03 Nov 2026

Editor's Note

Agents stop advising and start acting: glucose control, self-run alignment research, chromatin and transcriptome in one model.

 

Nº 01 · The Lede  —  arXiv  —  Agents · Infrastructure

DiabAgent aims AI agents at blood-glucose control

DiabAgent aims AI agents at blood-glucose control

Fig. I  arXiv · Filed 03 Nov 2026.

DiabAgent puts a language-model agent (software that plans and acts over several steps on its own) inside a physiological control loop, treating blood-glucose management as a task the agent runs rather than a question it answers. Automated glucose control already exists in closed-loop insulin pumps, but those controllers follow fixed algorithms. The case for agentic control is that a reasoning system can weigh context a fixed controller never sees, including meals, activity, and how a patient responded last time. The 'toward' in the arXiv paper is honest. This is framing and early machinery, not a clinical result.

Read the source →

Why it matters

Controlling a physiological variable is a different claim from analysis or advice. It puts agent output on the dosing side of the clinic, where the evidence needed is trial data, not benchmark scores.

 

Nº 02  —  arXiv  —  Agents · Infrastructure

Research agent tunes alignments for complex prediction

Fig. II  arXiv · Filed 03 Nov 2026.

Research agent tunes alignments for complex prediction

An agent runs its own research on multiple sequence alignments, searching for ways to organize and pair them that improve predicted structures of protein-protein complexes. Alignment construction is one of the few levers left in complex prediction, and groups have tuned it by hand for years. In this arXiv work the tuning is the agent's job: it proposes alignment strategies and evaluates them against prediction accuracy. Agents are starting to propose method changes, not only execute pipelines someone else designed.

Read more →

 

Nº 03  —  bioRxiv  —  Cell biology · Funding

Single-cell model links expression and chromatin state

Fig. III  bioRxiv · Filed 03 Nov 2026.

Single-cell model links expression and chromatin state

One model reads transcriptome and chromatin together, learning a shared representation across single-cell RNA and accessibility data so one modality can be analyzed in terms of the other. Most single-cell foundation models — general models trained broadly rather than built for one task — handle expression alone, leaving multiome data to separate integration tools. The bioRxiv preprint reports cross-modality analysis coming out of one pretrained model.

Read more →

 

Also Filed  ·  Three Briefs from the queue

Nº 04  —  bioRxiv  —  Structural biology · Protein design

Tuned protein models find dual-target peptides

Protein language models retuned cheaply pick out antimicrobial peptides active against two targets at once, with only a small fraction of model weights adjusted. Training and test sets were split under strict homology cutoffs, so near-identical sequences can't inflate the reported performance.

Read →

Nº 05  —  OpenAI  —  Field report

Anima cuts clinic call waits by 75%

Clinic call waits dropped 75% at practices using Anima, which builds patient-facing tools on OpenAI's GPT-6 and GPT-Live, according to OpenAI's customer write-up. What changed is how quickly patients reach a clinic, not what the clinic decides.

Read →

Nº 06  —  OpenAI  —  Agents · Infrastructure

OpenAI coordinates fixes as agents find critical bugs

Agents turned up critical vulnerabilities in open-source code, and OpenAI built Patch the Planet to route those findings to maintainers and incident responders ahead of disclosure. Much of the software research depends on is maintained by volunteers.

Read →

 

· · ·

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