Normalize a final answer to a quantitative reasoning question. Args: final_answer: The answer string to normalize Return

Extract the last LaTeX boxed expression from a string. Args: string: Input string containing LaTeX code Returns:

Remove the LaTeX boxed command from a string. Args: s: String with format "\\boxed{content}" Returns: The conten

Compute the reward score for a solution. Args: solution_str: The solution string ground_truth: The ground truth answer

Check if the solution is correct according to Minerva criteria. Args: solution_str: The solution string to check gt: The grou

Check if the prediction is correct using strict boxed answer criteria. Args: pred: The prediction string gt: The ground truth

Parses vLLM args based on CLI inputs. Currently uses argparse because vLLM doesn't expose Python models for all of the config options we want

Verify if the solution is correct. Args: solution_str: The solution string to verify answer: The ground truth answer

Builds the Serve app based on CLI arguments. See https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#command-line-arguments-for-

OpenAI-compatible HTTP endpoint. API reference: - https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html