Researchers have developed "El Agente Quntur," a multi-agent system utilizing GPT-5.6 Sol and GPT-5.6 Terra to automate the selection and refinement of active spaces for complex multi-reference calculations in computational chemistry. This agentic approach demonstrated a 48% reduction in mean absolute error compared to existing protocols by intelligently planning and executing calculations, selecting orbitals, and verifying convergence. While showing significant advantages over fixed workflows, the system still has room for improvement in efficiency, inter-agent communication, and decision-making criteria. AI
IMPACT Automates complex scientific workflows, potentially accelerating research in computational chemistry and related fields.
RANK_REASON The cluster contains a research paper detailing a novel application of AI agents in computational chemistry. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.MA (Multiagent) →
- Active Space Finder
- arXiv
- def2-TZVPD
- El Agente Quntur
- GPT-5.6 Sol
- GPT-5.6 Terra
- Juan B. Pérez-Sánchez
- multi-configurational self-consistent field
- NEVPT2
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →