DeepResearch RewardBench: Evaluating Reward Models for Deep Research Report
- Published
- Source
- arXiv
- Paper number
- 1428
- Field
- Research
- arXiv ID
- 2611.10156
Key points
- The authors built the first benchmark dedicated to evaluating reward modeling for research reports.
- Data collection kept only pairs with a score margin greater than 10/30 points to ensure discriminative challenge.
- The evaluation covers 19 models spanning diverse architectures and scales from 7B to 235B parameters.
- The evaluation encompasses 19 models spanning diverse architectures and scales from 7B to 235B parameters, categorized into three groups.
- The initial inter-annotator agreement stood at 63%, improving to approximately 85% after discussion.
- The authors expect the benchmark to serve as a testbed for research-oriented agents.
Paper links
External research summaries. These are not HDATF publications or measured product results.