QD-Rec: Evolving Diverse Reasons for Decisions with Quality-Diversity

Shows a way to search over reasons for choosing items from a fixed pool, using a bandit plus LLM mutation and crossover with a quality-diversity archive. Code is released, so agent builders can adapt it, though gains are measured only with LLM judges.

• LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

• articleMASS distills multi-agent workflows into a single self-improving model
• articleSakana's MLR benchmarks LLM peer review with planted contradictions
• postIntroducing PC-ALM, a local-learning alternative to backpropagation.
• postSakana AI Launches Fugu Max and Fugu Ultra v2 Model Orchestration

• articleオープンエンドな探索を意思決定支援へ：推薦の質と多様性を高める「QD-Rec」を提案Sakana AI
• blogGenRec: Towards LLM-Native Recommendation at NetflixNetflix Technology Blog
• postVLM agents replicate Picbreeder and fall short of human open-endednessSakana AI

Checking sign-in…

Loading comments…