def len_reward()

in src/open_r1/rewards.py [0:0]

• 46 lines of code
• 8 McCabe index (conditional complexity)

def len_reward(completions: list[Dict[str, str]], solution: list[str], **kwargs) -> float:
    """Compute length-based rewards to discourage overthinking and promote token efficiency.

    Taken from the Kimi 1.5 tech report: https://huggingface.co/papers/2501.12599

    Args:
        completions: List of model completions
        solution: List of ground truth solutions

    Returns:
        List of rewards where:
        - For correct answers: reward = 0.5 - (len - min_len)/(max_len - min_len)
        - For incorrect answers: reward = min(0, 0.5 - (len - min_len)/(max_len - min_len))
    """
    contents = [completion[0]["content"] for completion in completions]

    # First check correctness of answers
    correctness = []
    for content, sol in zip(contents, solution):
        gold_parsed = parse(
            sol,
            extraction_mode="first_match",
            extraction_config=[LatexExtractionConfig()],
        )
        if len(gold_parsed) == 0:
            # Skip unparseable examples
            correctness.append(True)  # Treat as correct to avoid penalizing
            print("Failed to parse gold solution: ", sol)
            continue

        answer_parsed = parse(
            content,
            extraction_config=[
                LatexExtractionConfig(
                    normalization_config=NormalizationConfig(
                        nits=False,
                        malformed_operators=False,
                        basic_latex=True,
                        equations=True,
                        boxed=True,
                        units=True,
                    ),
                    boxed_match_priority=0,
                    try_extract_without_anchor=False,
                )
            ],
            extraction_mode="first_match",
        )
        correctness.append(verify(answer_parsed, gold_parsed))

    # Calculate lengths
    lengths = [len(content) for content in contents]
    min_len = min(lengths)
    max_len = max(lengths)

    # If all responses have the same length, return zero rewards
    if max_len == min_len:
        return [0.0] * len(completions)

    rewards = []
    for length, is_correct in zip(lengths, correctness):
        lambda_val = 0.5 - (length - min_len) / (max_len - min_len)

        if is_correct:
            reward = lambda_val
        else:
            reward = min(0, lambda_val)

        rewards.append(float(reward))

    return rewards