2026-05-29原文

Frontier LLM-based agents can overcome the ontology curation bottleneck for natural phenotypes

A new study uses five frontier LLMs from Anthropic and OpenAI as 'agentic curators' in a self-contained workspace to automate phenotype annotation. The agents achieved consistency within the range of human curators and substantially outperformed traditional NLP tools, addressing the scalability bottleneck in ontology curation.

Article intelligence

EngineersAdvanced

Key points

Phenotype annotation relies on human experts, which is labor-intensive and hard to scale.
The study deployed five frontier LLMs as agentic curators in a self-contained workspace.
All agents performed within inter-curator variability; best agent approached but did not surpass top human curator.
Agents significantly outperformed the Semantic CharaParser NLP tool on all four metrics.

Why it matters

This matters because phenotype annotation relies on human experts, which is labor-intensive and hard to scale.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.28965] Frontier LLM-based agents can overcome the ontology curation bottleneck for natural phenotypes

[Submitted on 27 May 2026]

Title:Frontier LLM-based agents can overcome the ontology curation bottleneck for natural phenotypes

View a PDF of the paper titled Frontier LLM-based agents can overcome the ontology curation bottleneck for natural phenotypes, by James P. Balhoff and Hilmar Lapp

View PDF

Abstract:Linking free-text phenotype descriptions to ontology terms, typically referred to as phenotype annotation, is essential for the cross-study integration of comparative morphological data. This labor intensive process has heavily relied on highly trained human experts, which makes it challenging to scale and thus a key bottleneck. Dahdul et al. (2018) established a Gold Standard (GS) of Entity-Quality (EQ) annotations across seven phylogenetic studies and used it to evaluate three human curators and the Semantic CharaParser NLP tool with ontology-based semantic similarity metrics; they reported that machine-human consistency was significantly lower than inter-curator (human-human) consistency. Here we revisit that benchmark with five frontier hosted LLMs from Anthropic and OpenAI, each operating as an "agentic curator" within a self-contained workspace that supplies the source publication PDF, the same annotation guide used by the original human curators, the four project ontologies (UBERON, PATO, BSPO, GO), and a validation script. Evaluated against the same Gold Standard, every agent fell within the range of inter-curator variability of the three trained human biocurators of the original study; the best performing agents approached but did not reach the best performing human curator. Agents substantially outperformed Semantic CharaParser on all four metrics.

Comments: 7 pages, 2 figures

Subjects:

Artificial Intelligence (cs.AI)

ACM classes: I.2.7; I.2.4

Cite as: arXiv:2605.28965 [cs.AI]

(or arXiv:2605.28965v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.28965

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: James Balhoff [view email] [v1] Wed, 27 May 2026 18:08:46 UTC (962 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Frontier LLM-based agents can overcome the ontology curation bottleneck for natural phenotypes, by James P. Balhoff and Hilmar Lapp

View PDF

view license

Current browse context:

cs.AI

new | recent | 2026-05

Change to browse by:

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)