arXiv AI
GenoMAS: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 7
BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics
arXiv:2601. 21800v4 Announce Type: replace Abstract: We introduce BioAgent Bench, an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks.
arXiv Computation and Language
Oct 26
SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks
arXiv:2610.32441v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly capable of supporting scientific workflows, but their capabilities across diverse research activitie...
arXiv AI
Jun 12
Benchmarking AI Agents for Addressing Scientific Challenges Across Scales
arXiv:2606. 12736v1 Announce Type: new Abstract: AI agents are increasingly being developed to accelerate scientific discovery, yet their practical capabilities in real research settings remain poorly understood.
arXiv AI
Jun 4
SciDER: Scientific Data-centric End-to-end Researcher
arXiv:2603. 01421v3 Announce Type: replace Abstract: While large language models accelerate scientific discovery, existing agents face severe limitations in adaptability, domain generalization, and multimodal scalability, often struggling to autonomously process raw, domain-specific experimental data.
arXiv AI
Jul 14
NVAITC AI Scientist: A Governed End-to-End Research System -- A Hypertension GWAS Case Study
arXiv:2607. 11084v1 Announce Type: new Abstract: Agentic research systems are emerging as a new paradigm for coordinating scientific workflows beyond isolated model inference, code generation, or statistical analysis.
arXiv AI
Oct 16
OmicsBench: a long-horizon multi-turn benchmark of AI agents on research-study-scale bioinformatics
OmicsBench is a new long‑horizon, multi‑turn bioinformatics benchmark for AI agents, comprising 97 tasks that link 662 subtasks into directed acyclic graphs. Each subtask is a user turn scored deterministically, with optional in‑context feedback. Across 12 models, agents achieve mean scores between 0.43 and 0.67, revealing lower performance on dependent subtasks and highlighting qualitative failure modes through an unsupervised discovery pipeline.