6 min read

Agent discovery gets a second modality

Agent discovery gets a second modality
Nº 01 · The Lede X Agents · Infrastructure

Agents land small-molecule hits

Agents land small-molecule hits
Fig. IX · Filed 10 Aug 2026.

Agent-driven hit ID extends to small molecules, according to a post from @katyenko co-written with a collaborator, which frames it as the second validated modality after protein binders. Binder design leans on structure-prediction tools an agent can call directly; small-molecule hit-finding runs through noisier chemistry, sparser assay data, and a far larger search space. Clearing both from one loop is the difference between a single-modality demo and a general hit-identification capability, which is what discovery-platform pitches have promised for two years running. Validation specifics are thin in the post itself, so the strength of the claim rests on the writeup it points to.

Read the source

Biorisk argument gets sharper
Fig. IIX · Filed 10 Aug 2026.
Nº 02 X Computational biology

Biorisk argument gets sharper

Biorisk from sequence models is real, but the panicked reading of a recent result misses both the mechanism and the available mitigations, argues a widely-shared thread on protein and genome language models. The case made is that assessing the risk requires knowing what these models actually shortcut versus what still takes wet-lab work. Biosecurity policy on sequence-design models is being drafted right now, and blanket restrictions would land on the same open models that a large share of structure and function research depends on.

Read more
Agentic retrieval meets structured data
Fig. IIIbioRxiv · Filed 10 Aug 2026.
Nº 03 bioRxiv Agents · Infrastructure

Agentic retrieval meets structured data

Agentic retrieval of structured data gets a hard look in a new bioRxiv preprint, which names the failure modes agents hit when pulling records from biomedical databases and works through remedies. Structured sources punish the loose, text-shaped querying that language models default to, and retrieval sits underneath nearly every biomedical agent demo shipped so far. Treating it as the accuracy bottleneck rather than reasoning sets a more honest floor for any claim that an agent can query public databases end to end.

Read more
Also Filed · Four Briefs from the queue
Nº 04 Hacker News Agents · Infrastructure

Replayable jury traces agent influence

A replayable agent jury posted to Show HN records how each agent's argument shifted a group verdict, built on A2A (Agent2Agent, a spec for agents messaging each other). Decision provenance at that granularity is the missing piece before multi-agent review of experimental evidence earns anyone's trust.

Read
Nº 05 arXiv Field report

MetaboLLM targets metabolite graphs

MetaboLLM specializes a model for metabolomics, integrating biochemical knowledge and predicting metabolite graph structure. Metabolomics has trailed genomics in dedicated model tooling, and a domain-specific model narrows that gap for annotation and pathway inference.

Read
Nº 06 bioRxiv Field report

Peptide design goes distribution-aware

Peptide generation gets distribution-aware in a new framework that steers generated sequences toward functional relevance rather than novelty alone. Generative peptide design has produced plenty of plausible-looking sequences that die in assays, and scoring against the real distribution tightens the funnel ahead of synthesis.

Read
Nº 07 arXiv Agents · Infrastructure

Agentic orchestration reaches ICU prediction

Quantum time-series meets agents in QuanTiMedAI, which predicts cardiac arrest mortality with an agent guiding the modeling pipeline. Quantum-enhanced clinical prediction remains a research curiosity, but agent-as-orchestrator is now surfacing in ICU risk modeling.

Read

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

Agentic Discovery  ·  Nº 73  ·  10 Aug 2026

Editor's Note

Monday: agents notched a second discovery modality over the weekend, and the biorisk argument they'll inherit got sharper.

 

Nº 01 · The Lede  —  X  —  Agents · Infrastructure

Agents land small-molecule hits

Agents land small-molecule hits

Fig. I  X · Filed 10 Aug 2026.

Agent-driven hit ID extends to small molecules, according to a post from @katyenko co-written with a collaborator, which frames it as the second validated modality after protein binders. Binder design leans on structure-prediction tools an agent can call directly; small-molecule hit-finding runs through noisier chemistry, sparser assay data, and a far larger search space. Clearing both from one loop is the difference between a single-modality demo and a general hit-identification capability, which is what discovery-platform pitches have promised for two years running. Validation specifics are thin in the post itself, so the strength of the claim rests on the writeup it points to.

Read the source →

Why it matters

Agent-driven discovery now has two modalities on the board instead of one, which moves the burden of proof: the open question stops being whether agents can find hits and becomes which modalities a platform can show them in.

 

Nº 02  —  X  —  Computational biology

Biorisk argument gets sharper

Fig. II  X · Filed 10 Aug 2026.

Biorisk argument gets sharper

Biorisk from sequence models is real, but the panicked reading of a recent result misses both the mechanism and the available mitigations, argues a widely-shared thread on protein and genome language models. The case made is that assessing the risk requires knowing what these models actually shortcut versus what still takes wet-lab work. Biosecurity policy on sequence-design models is being drafted right now, and blanket restrictions would land on the same open models that a large share of structure and function research depends on.

Read more →

 

Nº 03  —  bioRxiv  —  Agents · Infrastructure

Agentic retrieval meets structured data

Fig. III  bioRxiv · Filed 10 Aug 2026.

Agentic retrieval meets structured data

Agentic retrieval of structured data gets a hard look in a new bioRxiv preprint, which names the failure modes agents hit when pulling records from biomedical databases and works through remedies. Structured sources punish the loose, text-shaped querying that language models default to, and retrieval sits underneath nearly every biomedical agent demo shipped so far. Treating it as the accuracy bottleneck rather than reasoning sets a more honest floor for any claim that an agent can query public databases end to end.

Read more →

 

Also Filed  ·  Four Briefs from the queue

Nº 04  —  Hacker News  —  Agents · Infrastructure

Replayable jury traces agent influence

A replayable agent jury posted to Show HN records how each agent's argument shifted a group verdict, built on A2A (Agent2Agent, a spec for agents messaging each other). Decision provenance at that granularity is the missing piece before multi-agent review of experimental evidence earns anyone's trust.

Read →

Nº 05  —  arXiv  —  Field report

MetaboLLM targets metabolite graphs

MetaboLLM specializes a model for metabolomics, integrating biochemical knowledge and predicting metabolite graph structure. Metabolomics has trailed genomics in dedicated model tooling, and a domain-specific model narrows that gap for annotation and pathway inference.

Read →

Nº 06  —  bioRxiv  —  Field report

Peptide design goes distribution-aware

Peptide generation gets distribution-aware in a new framework that steers generated sequences toward functional relevance rather than novelty alone. Generative peptide design has produced plenty of plausible-looking sequences that die in assays, and scoring against the real distribution tightens the funnel ahead of synthesis.

Read →

Nº 07  —  arXiv  —  Agents · Infrastructure

Agentic orchestration reaches ICU prediction

Quantum time-series meets agents in QuanTiMedAI, which predicts cardiac arrest mortality with an agent guiding the modeling pipeline. Quantum-enhanced clinical prediction remains a research curiosity, but agent-as-orchestrator is now surfacing in ICU risk modeling.

Read →

 

· · ·

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