data-science-agents

AdaPRA 提出了一种用于数据科学智能体的持久化编码框架与过程奖励智能体（PRA），通过自适应评分标准（rubrics）检测并纠正过程错误，使 80B Qwen 模型在 DSPredict 基准上的排名百分位提升了 24.5（Easy）和 14.8（Hard）个点。

AdaPRA introduces a persistent coding agent harness with adaptive rubric-guided process supervision that accumulates knowledge across attempts, boosting an 80B Qwen model's leaderboard percentile by 24.5 points on DSPredict-Easy and 14.8 on DSPredict-Hard while reducing process errors in data science agents.

This paper introduces a ground-truth-as-code framework for evaluating data-science agents on continuously updated data, achieving improved agreement with human evaluators and reduced token consumption.