QD-Rec: Open-Ended Evolution of Recommendations via Quality–Diversity
Blog: pub.sakana.ai
GitHub: SakanaAI/QD-Rec
arXiv: arxiv.org
Open-ended search has been used to discover algorithms, generate scientific ideas, and develop self-improving agents. With QD-Rec, we explore how it can support a different kind of task: helping people make decisions.
Which company should an acquirer buy? Which customers might benefit from a product? Which papers should a researcher read? In each case, the task is to choose among existing options, not generate new ones. At first glance, a finite, predefined candidate pool seems to leave little room for open-ended exploration.
However, a fixed set of options does not imply a fixed set of reasons for choosing them. The same company might be worth considering for its technology or its potential to open up a new market. The search over these reasons remains open-ended even when the options themselves are fixed.
QD-Rec searches over both what to recommend and why. Instead of aiming for a single best answer, it builds a diverse collection of recommendations, each pairing a candidate with a natural-language hypothesis explaining why it fits a particular decision maker’s goals, interests, and background.
The system combines three components. A contextual bandit learns which items to investigate next, balancing promising candidates with less-explored ones. An LLM generates hypotheses by adapting or combining the earlier recommendations. An archive retains new recommendations when they offer a novel reason, or replaces a similar recommendation when the new one is judged better.
We evaluate QD-Rec on acquisition target discovery, customer targeting, and paper recommendation. Compared with variants that remove evolutionary hypothesis generation or contextual bandits, QD-Rec achieves the highest mean LLM-rated quality in most settings and usually builds the largest archive. We also found examples where earlier recommendations with a low quality became stepping stones for later discoveries.
These experiments are a starting point. Practical applications will require richer, up-to-date information and expert human feedback to assess whether the proposed QD-Rec holds up beyond evaluation by an LLM judge.
We are releasing the code for QD-Rec so that researchers and practitioners can explore open-ended recommendation with their own decision-making tasks.
89 likes · 13 reposts · 6,616 views
Mentions
We also released the code, and we'd love for you to try it on your own problems! SakanaAI/QD-Rec Finally, I am very grateful to Taro Makino and Issa Sugiura, I had a lot of fun working on this project!
Excited to share QD-Rec @sakanaai.bsky.social, our new work on open-ended recommendation for decision-making with quality-diversity!! Blog: pub.sakana.ai Code: SakanaAI/QD-Rec Paper: arxiv.org Thread below 🧵.
@0xMassi @SakanaAILabs For the released code, I'd refresh the input CSV first. The README supports your own LSEG export or another source; item_text in apps/companies/items.py picks the fields the models see. SakanaAI/QD-Rec
QD-Rec: Open-Ended Evolution of Recommendations via Quality–Diversity Blog: pub.sakana.ai GitHub: SakanaAI/QD-Rec arXiv: arxiv.org Open-ended search has been used to discover algorithms, generate scientific ideas, and develop self-improving agents. With QD-Rec, we explore how it can support a different kind of task: helping people make decisions. Which company should an acquirer buy? Which customers might benefit from a product? Which papers should a researcher read? In each case, the task is to choose among existing options, not generate new ones. At first glance, a finite, predefined candidate pool seems to leave little room for open-ended exploration. However, a fixed set of options does not imply a fixed set of reasons for choosing them. The same company might be worth considering for its technology or its potential to open up a new market. The search over these reasons remains open-ended even when the options themselves are fixed. QD-Rec searches over both what to recommend and why. Instead of aiming for a single best answer, it builds a diverse collection of recommendations, each pairing a candidate with a natural-language hypothesis explaining why it fits a particular decision maker’s goals, interests, and background. The system combines three components. A contextual bandit learns which items to investigate next, balancing promising candidates with less-explored ones. An LLM generates hypotheses by adapting or combining the earlier recommendations. An archive retains new recommendations when they offer a novel reason, or replaces a similar recommendation when the new one is judged better. We evaluate QD-Rec on acquisition target discovery, customer targeting, and paper recommendation. Compared with variants that remove evolutionary hypothesis generation or contextual bandits, QD-Rec achieves the highest mean LLM-rated quality in most settings and usually builds the largest archive. We also found examples where earlier recommendations with a low quality became stepping stones for later discoveries. These experiments are a starting point. Practical applications will require richer, up-to-date information and expert human feedback to assess whether the proposed QD-Rec holds up beyond evaluation by an LLM judge. We are releasing the code for QD-Rec so that researchers and practitioners can explore open-ended recommendation with their own decision-making tasks.
多様な提案を進化させ、意思決定を支える推薦手法「QD-Rec」を開発 ブログ：sakana.ai 論文：arxiv.org GitHub：SakanaAI/QD-Rec どの企業を買収候補として検討するか。どの顧客に新しい製品を提案するか。膨大な論文の中から、次に何を読むか。こうした意思 決定では、候補をスコア順に並べるだけでなく、「なぜ選ぶのか」「選んだ先にどのような可能性があるのか」を、異なる観点から比較できることが重要です。 一つの候補にも複数の有望な理由が考えられます。数千件、ときには1万件を超える候補それぞれについて、さまざまな仮説を生成・評価し尽くすには大きなコストがかかります。私たちは、限られた予算の中で「候補」と「仮説」の組を探索し、質が高く多様な提案を見つける問題を「オープンエンドな推薦」として捉えました。 QD-Recは、オープンエンドな探索の研究で発展してきた「Quality-Diversity（QD）」と呼ばれる進化的探索技術を、推薦に応用します。過去の評価結果をもとに次に調べる候補を選び、蓄積された仮説の着眼点をLLMが別の候補に応用したり、複数の仮説を組み合わせたりして、新しい提案を生成します。新しい切り口の提案は残し、似た提案同士ではより優れたものに更新することで、多様な仮説を次の発見の「踏み石」として活かし、推薦の集合を進化させていきます。 実験では、 企業の買収候補探索、架空の顧客プロファイルを使ったターゲティング、研究者向けの論文推薦などで検証しました。同じ評価回数のもとで比較したところ、多くの設定で、比較手法よりもQD-Recの方が評価が高く、より多様で多くの推薦を蓄積できました。 私たちが目指すのは、AIが人間の意思決定を代行することではなく、多様で有望な選択肢と、それらを比較・検討するための判断材料を提供することです。今回の成果を出発点に、QD-Recを次世代の意思決定を支える基盤技術へと発展させていきます。