# Autonomous Multi-Agent AI for High-Throughput Polymer Informatics: From Property Prediction to Generative Design Across Synthetic and Bio-Polymers

arXiv: https://arxiv.org/abs/2602.00103 · HTML: https://mlsanity.com/paper/2602.00103/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 4 of its 43 references that are in the map.
- First posted on arXiv 25 Jan 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 4 of 4)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [34 Examples of LLM Applications in Materials Science and Chemistry: Towards Automation, Assistants, Agents, and Accelerated Scientific Discovery](https://mlsanity.com/paper/2505.03049/) (2025)
- [Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry](https://mlsanity.com/paper/2411.15221/) (2024)

## Built on by (most cited first, 1 of 1)

- [From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry](https://mlsanity.com/paper/2605.03205/) (2026)

## Abstract (arXiv)

We present an integrated multiagent AI ecosystem for polymer discovery that unifies high-throughput materials workflows, artificial intelligence, and computational modeling within a single Polymer Research Lifecycle (PRL) pipeline. The system orchestrates specialized agents powered by state-of-the-art large language models (DeepSeek-V2 and DeepSeek-Coder) to retrieve and reason over scientific resources, invoke external tools, execute domain-specific code, and perform metacognitive self-assessment for robust end-to-end task execution. We demonstrate three practical capabilities: a high-fidelity polymer property prediction and generative design pipeline, a fully automated multimodal workflow for biopolymer structure characterization, and a metacognitive agent framework that can monitor performance and improve execution strategies over time. On a held-out test set of 1,251 polymers, our PolyGNN agent achieves strong predictive accuracy, reaching R2 = 0.89 for glass-transition temperature (Tg ), R2 = 0.82 for tensile strength, R2 = 0.75 for elongation, and R2 = 0.91 for density. The framework also provides uncertainty estimates via multiagent consensus and scales with linear complexity to at least 10,000 polymers, enabling high-throughput screening at low computational cost. For a representative workload, the system completes inference in 16.3 s using about 2 GB of memory and 0.1 GPU hours, at an estimated cost of about 0.08. On a dedicated Tg benchmark, our approach attains R2 = 0.78, outperforming strong baselines including single-LLM prediction (R2 = 0.67), group-contribution methods (R2 = 0.71), and ChemCrow (R2 = 0.66). We further demonstrate metacognitive control in a polystyrene case study, where the system not only produces domain-level scientific outputs but continually monitors and optimizes its own behavior through tactical, strategic, and meta-strategic self-assessment.