---
type: "post"
id: "qd-rec-open-ended-evolution-of-recommendations-via-89ff95"
slug: "qd-rec-open-ended-evolution-of-recommendations-via-89ff95"
title: "QD-Rec: Open-Ended Evolution of Recommendations via Quality–Diversity"
description: "Sakana AI has published QD-Rec, a method for generating a set of diverse recommendations from a fixed candidate pool."
retrieval_nugget: "Sakana AI has published QD-Rec, a method for generating a set of diverse recommendations from a fixed candidate pool."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["models","personalization"]
entities: ["Sakana AI","QD-Rec","Walt Disney","JPMorgan Chase"]
related_patterns: ["model-answers-become-task-interfaces"]
novelty_label: "same_event"
what_changed: "Same event as Sakana AI released QD-Rec, a Quality-Diversity recommender that evolves item plus reason pairs instead of ranking."
prior_refs: ["memory:37996e3e-6f99-8882-a105-69c8caec6084","memory:d0115296-aee4-82be-af43-11ca3806acff"]
source_url: "https://pub.sakana.ai/qd-rec"
source_urls: ["https://pub.sakana.ai/qd-rec"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:qd-rec-open-ended-evolution-of-recommendations-via-89ff95"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/qd-rec-open-ended-evolution-of-recommendations-via-89ff95/","markdown":"https://newruntime.com/posts/qd-rec-open-ended-evolution-of-recommendations-via-89ff95.md","json":"https://newruntime.com/posts/qd-rec-open-ended-evolution-of-recommendations-via-89ff95.json"}
---

# QD-Rec: Open-Ended Evolution of Recommendations via Quality–Diversity

## Retrieval answer

Sakana AI has published QD-Rec, a method for generating a set of diverse recommendations from a fixed candidate pool.

Sakana AI has published QD-Rec, a method for generating a set of diverse recommendations from a fixed candidate pool. Its search unit is an item-hypothesis pair: a candidate and a natural-language explanation of why it fits a decision maker. The system maintains an archive, repeatedly selects an item, generates a hypothesis from earlier entries, and decides whether to retain it.

QD-Rec uses a contextual bandit to choose items, with an additional diversity bonus. A proposer model can mutate, combine, or explore ideas from three archive examples. An LLM evaluator retains a proposal if it is novel relative to nearby archive entries; otherwise it uses a blind pairwise comparison against its closest neighbor.

The reported tests include acquisition-target search across about 6,300 US companies for Walt Disney and JPMorgan Chase, marketing over 10,000 fictional customer profiles, and paper recommendation over 17,500 recent conference papers. The company reports higher archive scores in some M&A and marketing tests, but little difference in the paper task. The source does not establish performance in real acquisition, marketing, or research workflows: evaluations rely on language-model judges, and part of the evaluation uses fictional profiles.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- topic hub: [Personalization](https://newruntime.com/topics/personalization.md): Explore the personalization topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)