Call for Papers

Overview & scope

AgenticLS focuses on agentic life-science systems as a building, deployment, and evaluation problem, with explicit attention to closed-loop discovery. We invite original, unpublished work on the design, benchmarking, and deployment of tool-using, reasoning, and multi-agent AI systems for biology and drug discovery. Submissions may span methods, systems, benchmarks, empirical studies, position papers, and applications.

Track I — Building Agentic Systems for Life Science

• Agent architectures & reasoning patterns: 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; scientific knowledge grounding.
• Agentic literature & knowledge systems: hypothesis generation, evidence synthesis, claim verification, protocol assistance, ontology-aware reasoning, knowledge-graph-enhanced agents.
• Generalist vs. specialist comparisons: foundation-model backbones, biology-specific instruction tuning, domain adaptation, and the role of biological foundation models inside agent pipelines.
• Reinforcement learning for scientific agents, including RL from lab-in-the-loop feedback and reward-function design for discovery.
• Recursive self-improvement for bio-specialized models: using general-purpose LLMs to iteratively improve specialized models through data generation/curation, automated evaluation, and feedback-driven refinement.

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, and system-level benchmarks.
• Reliability, governance & biosafety: hallucinated biology, biosecurity-aware safeguards, human oversight, traceability, auditability, and deployment standards for scientific agents.