RESEARCHMonitorNEXT 12 MONTHS
SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Researchers introduced SCHEDBench, a benchmark of 1,132 instances evaluating LLM reliability in solving combinatorial scheduling tasks.
Open source