Agentic Swarms Discover Enhanchment of Fractional Chern Insulator Gaps Beyond Ideal Quantum Geometry
Abstract
Can artificial intelligence (AI) move beyond solving well-defined problems to contribute to open-ended discovery in fundamental physics? Could AI propose what to explore, identify unexpected phenomena, and uncover their mechanisms? We address this using MOSAIC (Multi-agent Open-ended Scientific Analysis and Investigation through Collaboration), a collaborative swarm of AI agents (Claude Opus 5.5), to tackle a longstanding bottleneck: the small energy gaps limiting the robustness of fractional topological order and the study of anyons at higher temperatures. Rather than prescribing a model, we ask frontier models (GPT-6 Astra) to propose a theoretical framework, which MOSAIC explores through diverse strategies and rapid exchange of ideas. This reveals a striking finding: although ideal quantum geometry is considered favorable for fractional states, departing from this limit can dramatically enhance their robustness, with many-body gaps more than an order of magnitude larger than in the ideal case. Without centralized coordination, the agents explored autonomously, combined findings across agents, and formed insights from individual runs, outperforming isolated agents with the same tools. AI-assisted theoretical analysis further develops simplified models with an analytical gap enhancement factor that is unbounded within the single-band approximation. Remarkably, AI identifies the real-space quantum metric, rather than the momentum-space one, as the key quantity governing the many-body gap, revealing how flat-band wavefunctions shape two-electron interactions and yielding an index computable from single-particle wavefunctions without many-body ED to guide gap optimization. Our study demonstrates how collaborative AI agents can integrate exploration, discovery of unexpected physics, and theoretical understanding, opening new possibilities for AI-driven research in fundamental physics.
Related
- Haldane-Holstein model at fractional filling: Route to bosonic fractional Chern insulator and quantum anomalous Hall crystal
- Chiral p-Wave Superconductivity Proximate to a Fractional Chern Insulator and a Topological Charge Density Wave in a Moiré Chern Band
- Direct transition from a fractional Chern insulator to a topological superconductor
- Is the fractional Chern insulator-superconductor transition in twisted MoTe2 direct?
- Preparation of a Laughlin-like fractional Chern insulator on a superconducting quantum processor
BibTeX
@misc{zhang2026agentic,
title = {{Agentic Swarms Discover Enhanchment of Fractional Chern Insulator Gaps Beyond Ideal Quantum Geometry}},
author = {Yitong Zhang and Changwen Xu and Andrew Boshi Li and Siddhartha Sarkar and Kai Sun and Venkatasubramanian Viswanathan},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.35934},
eprint = {2610.35934},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.35934},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Agentic Swarms Discover Enhanchment of Fractional Chern Insulator Gaps Beyond Ideal Quantum Geometry
AU - Yitong Zhang
AU - Changwen Xu
AU - Andrew Boshi Li
AU - Siddhartha Sarkar
AU - Kai Sun
AU - Venkatasubramanian Viswanathan
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.35934
UR - https://arxiv.org/abs/2610.35934
AB - Can artificial intelligence (AI) move beyond solving well-defined problems to contribute to open-ended discovery in fundamental physics? Could AI propose what to explore, identify unexpected phenomena, and uncover their mechanisms? We address this using MOSAIC (Multi-agent Open-ended Scientific Analysis and Investigation through Collaboration), a collaborative swarm of AI agents (Claude Opus 5.5), to tackle a longstanding bottleneck: the small energy gaps limiting the robustness of fractional topological order and the study of anyons at higher temperatures. Rather than prescribing a model, we ask frontier models (GPT-6 Astra) to propose a theoretical framework, which MOSAIC explores through diverse strategies and rapid exchange of ideas. This reveals a striking finding: although ideal quantum geometry is considered favorable for fractional states, departing from this limit can dramatically enhance their robustness, with many-body gaps more than an order of magnitude larger than in the ideal case. Without centralized coordination, the agents explored autonomously, combined findings across agents, and formed insights from individual runs, outperforming isolated agents with the same tools. AI-assisted theoretical analysis further develops simplified models with an analytical gap enhancement factor that is unbounded within the single-band approximation. Remarkably, AI identifies the real-space quantum metric, rather than the momentum-space one, as the key quantity governing the many-body gap, revealing how flat-band wavefunctions shape two-electron interactions and yielding an index computable from single-particle wavefunctions without many-body ED to guide gap optimization. Our study demonstrates how collaborative AI agents can integrate exploration, discovery of unexpected physics, and theoretical understanding, opening new possibilities for AI-driven research in fundamental physics.
ER -