LN — From AI for Science to Agentic Science (Zhang et al., 2025)
Full Reference: Zhang, X., et al. (2025). From AI for science to Agentic Science: A survey on autonomous scientific discovery. arXiv preprint arXiv:2508.14111. https://doi.org/10.48550/arXiv.2508.14111
Pass 1 — Bird’s Eye
Type: Survey paper Main Claim: “Agentic Science” represents a new research paradigm where AI systems manage complete investigation cycles — from hypothesis to conclusion — with limited human oversight. Relevance to PUMA: ⭐⭐⭐⭐ High — provides the theoretical framework for classifying PUMA’s Smart PMO as applied Agentic Science.
Pass 2 — Key Content
Three-Phase Framework (aligned with LeCun’s levels)
- AI for Science (tool phase): Domain-specific models, literature synthesis, data analysis
- AI in Science (collaborative phase): Co-pilot systems, closed-loop experiments in specific domains
- Agentic Science (autonomous phase): AI agents manage full research cycles across domains
Key Application Domains Surveyed
- Life Sciences: drug discovery, protein design, genomics
- Chemistry: synthesis planning, catalyst design, reaction prediction
- Materials: crystal structure prediction, property optimization
- Physics: model discovery, simulation acceleration
Critical Requirements for Agentic Science
- Hypothesis formulation: Ability to generate specific, testable predictions
- Experiment planning: Selection of experimental conditions to maximally inform hypotheses
- Data interpretation: Automated extraction of conclusions from experimental data
- Knowledge integration: Grounding new results in the existing knowledge base
Identified Challenges
- Scalability of data infrastructure for robotic experiments
- Interpretability of AI-generated discoveries
- Attribution and credit for AI contributions
- Reproducibility of stochastic AI experiments
Pass 3 — PUMA Re-implementation
The survey’s framework maps directly to PUMA’s research design:
- PUMA Phase 1 (Research) = “AI for Science” phase: using AI tools for literature synthesis
- PUMA Phase 2 (Development) = “AI in Science” phase: building the benchmark with AI assistance
- PUMA Stage 5 (Smart PMO) = “Agentic Science” phase: autonomous PM workflow cycles
MIT Critical Questions
- How can I use this? → Cite in PUMA Section 1.1 to position PUMA within the Agentic Science trajectory.
- Does it really support its claims? → Yes — well-documented with concrete examples per domain.
- What if PM doesn’t fit this framework? → PM lacks the “ground truth” verification mechanism of physical experiments; PUMA addresses this with labeled datasets (Jira SR, TAWOS).
APA7 Citation
Zhang, X., et al. (2025). From AI for science to Agentic Science: A survey on autonomous scientific discovery. arXiv preprint arXiv:2508.14111. https://doi.org/10.48550/arXiv.2508.14111
Related Notes
- PN-Agentic-Science-Paradigm — synthesised permanent note from this survey
- PN-AI-Scientific-Knowledge-Generation — evidence of AI knowledge generation
- PN-PUMA-within-AgenticScience-Trajectory — PUMA’s position in this trajectory
- LN-Lu-2024-AIScientist
- LN-Felin-2024-TheoryIsAllYouNeed — counter-argument
- Smart-PMO-Vision — PUMA Stage 5 as Agentic Science for PM
- PR-PUMA-Ch1-Introduction — cited in §1.1 context