CO-Bench/CO-Bench

CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization This dataset contains the data for the paper CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization. Code: github.com/sunnweiwei/CO-Bench Introduction In this paper, we introduce CO-Bench, a benchmark suite featuring 36 real-world Combinatorial Optimization (CO) problems drawn from a broad range of domains and complexity levels.… See the full description on the dataset page: huggingface.co/datasets/CO-Bench/CO-Bench.