Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists
- Published
- Source
- arXiv
- Paper number
- 1430
- Field
- Research Agents
- arXiv ID
- 2611.12184
Key points
- The authors deliberately limited task information to push idea generation away from familiar approaches.
- They learn from proposals previously verified on the same task and their outcomes to retain promising candidates.
- They evaluated the framework across five proposer models and 12 scientific tasks.
- At a discard ratio of 50%, the selective-retention model preserves 79% of the top-5% proposals by creativity and 82% by utility.
- Five PhD-level researchers each annotated 30 proposal pairs, yielding 150 pairs in total.
- As task information increases, the share of highly creative proposals in the top 1% decreases, supporting the creativity benefit of limited information.
Paper links
External research summaries. These are not HDATF publications or measured product results.