Benchmarking NM-SRN v2.0 AGI on the Job-Shop Scheduling Problem (JSSP)
Abstract We present benchmark results for the NM-SRN v2.0 AGI architecture on two canonical instances of the Job-Shop Scheduling Problem (JSSP). Using structured, evolutionary search guided by neural resonance (RE-S), NM-SRN achieved a makespan of 421 on a 10-job, 5-machine instance, and 2621 on a 50-job, 10-machine instance. These results establish a new standard for solvable, traceable solutions to NP-hard scheduling problems using transparent AGI frameworks.
Institutions
- Biokine (Israel) (IL)
- Neural Signals (United States) (US)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2025-06-10
- DOI
- https://doi.org/10.5281/zenodo.15628240
- Primary Topic
- Scheduling and Optimization Algorithms
- Type
- article
- Field-Weighted Citation Impact
- 0.00