Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• DScheLLM is a dynamic scheduling approach that uses a fine-tuned large language model within a dual-system (fast-slow) reasoning architecture.method 70%
• Training datasets for the fast and slow reasoning modes of DScheLLM are generated using exact schedules from an operations research solver.method 70%
• The Huawei OpenPangu Embedded-7B model is fine-tuned using LoRA for DScheLLM's hybrid reasoning paradigms.method 70%
• The fast-thinking mode of DScheLLM can efficiently generate high-quality schedules.result 70%
• The slow-thinking mode of DScheLLM can produce solver-compatible and well-formatted decision inputs.result 70%
• Conventional production scheduling approaches have limited adaptability and generalization to unseen disturbances.limitation 70%
• This work is among the earliest studies applying large language models to job shop scheduling in dynamic environments.technical 70%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card