PigGPA: A Domain-Constrained Agent for Porcine Genomic Breeding with Verifiable Tool Execution
- 1Chinese Academy of Agricultural Sciences
Abstract
Large language model agents can plan and execute scientific analyses, but successful task completion does not establish whether analytical decisions remain consistent across independent sessions or whether computations follow the parameters specified beforehand. We investigated these limitations using four genomic analysis tasks. General-purpose agents showed limited consistency in analytical decisions across repeated sessions (57.5-58.8%). Incorporating domain knowledge improved analytical performance, with reusable skills increasing mean evaluation scores from 73.44 to 89.06/100 , but did not resolve decision variability or ensure agreement between specified and executed parameters. To address these limitations, we developed an approach combining domain-constrained analytical skills with call-level execution contracts. Each tool invocation is linked to a pre-execution parameter declaration through SHA-256 hashing, with actual command-line arguments and execution records subsequently checked against the declared parameters. We implemented this approach in PigGPA, an autonomous agent for porcine genomic breeding that integrates statistical genetics, sequence-based functional prediction and multi-omics annotation. PigGPA completed all benchmark tasks with full agreement between declared and executed parameters, while its core quantitative-genetic results closely matched established software (r = 0.999-1.000). An application to loin muscle depth further demonstrated an integrated workflow from genetic association analysis to functional interpretation. These findings show that domain knowledge improves analytical performance, while direct verification of tool execution provides an additional basis for reproducible scientific computation.
Related
- Sugarcane breeding array 1.0: A high‐density SNP chip for genomic studies and molecular breeding
- YGEP: An Integrated Web Platform for Genomic Evaluation and Intelligent Breeding in Yak
- VariantFlow: a selective-execution engine for efficient population genomic computation on large variant datasets
- A unified decision framework combines phenotypic and genomic information for nonlinear selection in plant breeding
- Optimizing progeny allocation strategies in breeding schemes while updating genomic prediction models.
BibTeX
@misc{liang2026piggpa,
title = {{PigGPA: A Domain-Constrained Agent for Porcine Genomic Breeding with Verifiable Tool Execution}},
author = {C. Liang and Y. Zhang and W. Wei and Z. Wang and K. Li},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.18.759908},
url = {https://www.biorxiv.org/content/10.64898/2026.10.18.759908v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - PigGPA: A Domain-Constrained Agent for Porcine Genomic Breeding with Verifiable Tool Execution
AU - C. Liang
AU - Y. Zhang
AU - W. Wei
AU - Z. Wang
AU - K. Li
PY - 2026
DA - 2026/10/18
PB - bioRxiv
DO - 10.64898/2026.10.18.759908
UR - https://www.biorxiv.org/content/10.64898/2026.10.18.759908v1
AB - Large language model agents can plan and execute scientific analyses, but successful task completion does not establish whether analytical decisions remain consistent across independent sessions or whether computations follow the parameters specified beforehand. We investigated these limitations using four genomic analysis tasks. General-purpose agents showed limited consistency in analytical decisions across repeated sessions (57.5-58.8%). Incorporating domain knowledge improved analytical performance, with reusable skills increasing mean evaluation scores from 73.44 to 89.06/100 , but did not resolve decision variability or ensure agreement between specified and executed parameters. To address these limitations, we developed an approach combining domain-constrained analytical skills with call-level execution contracts. Each tool invocation is linked to a pre-execution parameter declaration through SHA-256 hashing, with actual command-line arguments and execution records subsequently checked against the declared parameters. We implemented this approach in PigGPA, an autonomous agent for porcine genomic breeding that integrates statistical genetics, sequence-based functional prediction and multi-omics annotation. PigGPA completed all benchmark tasks with full agreement between declared and executed parameters, while its core quantitative-genetic results closely matched established software (r = 0.999-1.000). An application to loin muscle depth further demonstrated an integrated workflow from genetic association analysis to functional interpretation. These findings show that domain knowledge improves analytical performance, while direct verification of tool execution provides an additional basis for reproducible scientific computation.
ER -