The authors use task rubrics as a common reference for evaluating both completed reports and intermediate tool use.
Rubric-based process rewards improve deep research agents’ evidence gathering
Dr.Credit rewards tool calls for adding new rubric-relevant evidence, rather than assigning every research step the final report’s score.
Chinese Tech
Yingjian Zhu · Zhenyi Wang · Jiaxin Guo · Kun Ding · Ying Wang · Shen Huang · +3 more
University of Chinese Academy of Sciences · State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) · Institute of Automation, Chinese Academy of Sciences · Alibaba Token Hub, Alibaba Group · Peking University
Research Digest··2 min read
Zhu et al.
Why this paper
From University of Chinese Academy of Sciences and 4 others
In one line
Rubric-grounded process credit, which tracks accumulated support per rubric, improves deep research agent performance and enables an 8B model to match proprietary systems.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§