Research
QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity
arXiv:2610.23470v1 Announce Type: cross Abstract: Open-ended search combined with foundation models has produced advances such as faster algorithms, new results on open mathematical problems, and self
arXiv:2610.23470v1 Announce Type: cross Abstract: Open-ended search combined with foundation models has produced advances such as faster algorithms, new results on open mathematical problems, and self-improving agents. We extend this paradigm to recommendation for decision-making, focusing on decisions where the set of possible choices is fixed but the reasons for choosing them are not. In high-stakes decisions, e.g., which company to acquire or which customer to target, comparing diverse, well-reasoned options can be more useful than a single ranked list. We formalize open-ended recommendation as building a diverse, high-quality set of recommendations, each an item together with a hypothesis, a natural-language reason why the item fits the needs of a decision maker. We propose QD-Rec, a quality--diversity method that selects items with a contextual bandit and generates hypotheses with a foundation model from earlier ones kept in an archive as stepping stones. A new recommendation enters the archive if it is novel or better than its nearest neighbor. Across M&A, customer targeting, and paper and book recommendation, QD-Rec gives the highest mean quality and builds the largest archive in most settings.
Related
- Evolving Towards Better Codes: LLM-Guided Search for High-Distance Binary Linear Codes
- More Is Not More: What Matters for Diversity in LLM Opinions?
- Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs
- Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
Source: arXiv cs.AI | 2026-10-19