NeurIPS 2026
NeurIPS 2026 Workshop · Sydney

Agentic AI for Biological Discovery (AgenticLS)

From scientific copilots to closed-loop labs: building, benchmarking, and deploying agentic AI systems for the next generation of life-science discovery.

Date
December 11, 2026
Location
Sydney, Australia
Venue
NeurIPS 2026
Submissions due
Sep 26, 2026 (AoE)
Call for Papers View Schedule

About the workshop

The life sciences are entering an era of agentic AI — systems built on tool-using and reasoning frameworks that go beyond static prediction to read literature, call specialized tools, plan multi-step analyses, propose experiments, and in some cases interact directly with laboratories and robotics. This shift is enabled both by frontier LLMs and by a rapidly growing stack of biology-specialized foundation models for proteins, genomes, and single cells.

Yet the field remains strikingly young. There is still little consensus on how to build effective life-science agents, when biology-specialized models are necessary versus when general-purpose LLMs suffice, and how to deploy such agents toward the ultimate goal: accelerating biological discovery and drug development. AgenticLS brings together researchers from machine learning, computational biology, experimental biology, drug discovery, and lab automation to tackle these questions as a building, deployment, and evaluation problem.

1

Building agents for discovery

How should we design agent harnesses, orchestrate multi-agent systems, manage long-horizon memory and context, and integrate biological tool ecosystems? What metrics and rewards guide agents toward novel discoveries?

2

Generalist vs. specialist

When are frontier general-purpose models (e.g., GPT, Claude) sufficient, and when do biology-specialized models (e.g., AlphaFold, ESM) materially improve planning, reasoning, or downstream outcomes — and can specialists improve via recursive self-improvement?

3

Autonomous lab-in-the-loop

How should agentic AI autonomously interface with robotics, assay platforms, and human scientists to enable reliable, iterative experimentation in closed-loop laboratories?

Scope & topics

We welcome submissions across two tracks spanning the full agentic life-science stack.

Track I — Building Agentic Systems for Life Science

  • Agent architectures & reasoning: LLM-based, multimodal, and retrieval-augmented agents; long-horizon planners; multi-agent scientific collaborations.
  • Harness design & orchestration: tool ecosystems and APIs for biology, multi-agent communication and routing, long-horizon memory and context management, knowledge grounding.
  • Agentic literature & knowledge systems: hypothesis generation, evidence synthesis, claim verification, protocol assistance, ontology-aware and knowledge-graph-enhanced agents.
  • Generalist vs. specialist comparisons: foundation-model backbones, bio-specific instruction tuning, domain adaptation, biological foundation models inside agent pipelines.
  • Reinforcement learning for scientific agents: RL from lab-in-the-loop feedback and reward-function design for discovery.
  • Recursive self-improvement for bio-specialized models: data generation and curation, automated evaluation, feedback-driven refinement, model-in-the-loop workflows.

Track II — Closed-Loop Discovery & Applications

  • Lab-in-the-loop & robotics: closed-loop experimentation, robotic execution, active learning, adaptive experiment planning, autonomous laboratories that learn from wet-lab feedback.
  • Agents for biological design & discovery: target identification, sequence and molecular design, structure-based design, CRISPR / perturbation design, assay planning, therapeutic optimization.
  • Evaluation & benchmarks: faithfulness, reproducibility, calibrated uncertainty, expert judgment, simulator-to-lab transfer, biological validity, system-level benchmarks.
  • Reliability, governance & biosafety: hallucinated biology, biosecurity-aware safeguards, human oversight, traceability, auditability, and deployment standards for scientific agents.

Key dates

Submission deadline
September 26, 2026 (AoE)
Author notification
September 29, 2026 (AoE)
Camera-ready
Mid-October 2026
Workshop day
December 11, 2026

Read the full Call for Papers →

Invited speakers

Confirmed invited speakers for talks spanning biomedical AI agents, biology-specialized foundation models, and autonomous laboratories.

Jure Leskovec
Jure Leskovec
Professor, Stanford University
Biomedical AI agents; knowledge graphs
Maria Brbić
Maria Brbić
Assistant Professor, EPFL
Foundation models & agents for cell biology
Heng Ji
Heng Ji
Professor, UIUC
Agentic AI for science; LLM reasoning
Joy Jiao
Joy Jiao
Life Sciences Research Lead, OpenAI
Agentic AI for life sciences
Michelle Lee
Michelle Lee
CEO & Founder, Medra AI
Physical-AI scientist; robotic closed-loop biology

Panelists

A 50-minute panel on the generalist-vs.-specialist debate and the “how to build” question.

Marinka Zitnik
Marinka Zitnik
Associate Professor, Harvard Medical School
Agentic AI for biology & medicine
Eli Carrami
Eli Carrami
Staff Research Scientist, Isomorphic Labs
AI for drug discovery (industry deployment)
Tommaso Biancalani
Tommaso Biancalani
SVP, Generative Biology, Lila Sciences
Lab-in-the-loop AI; foundation models for biology

Meet the organizers →

Get involved

Help us build a rigorous, inclusive forum for agentic AI in the life sciences.

Call for reviewers

We welcome researchers and practitioners with expertise in machine learning, AI agents, computational biology, drug discovery, and laboratory automation to help review workshop submissions.

Sign up as a reviewer →

Sponsorship opportunities

We warmly welcome sponsors who share our vision of accelerating biological discovery through responsible agentic AI. Sponsorship helps us support an accessible, high-quality workshop and bring together researchers across academia and industry.

Contact us about sponsorship →