Universe of Thoughts: Teaching AI to Think Creatively

Kari Jaaskelainen

26 Nov 2025 — 1 min read

LLMs are great at step-by-step "chain-of-thought" logic, but real breakthroughs need creative reasoning. This paper introduces Universe of Thoughts (UoT): a framework, inspired by cognitive science, that teaches AI to explore many idea paths—not just the obvious ones.

Combinational: mix existing ideas in novel ways.
Exploratory: push deeper into the solution space to surface unexpected options.
Transformative: reframe the rules of the problem to unlock new directions.

The authors also propose new tasks and a benchmark that score creativity on three fronts: feasibility (meets constraints), utility (useful outcomes), and novelty (originality). Across these tests, UoT outperforms state-of-the-art reasoning methods and leading commercial models on creative problem-solving.

Why it matters: In fields with huge search spaces—like drug design or market strategy—finding the surprising, workable idea is everything. UoT shows a path for AI systems that do not just follow steps, but imagine better steps.

Paper: https://arxiv.org/abs/2511.20471v1

Paper: https://arxiv.org/abs/2511.20471v1

Register: https://www.AiFeta.com

#AI #LLM #Creativity #Reasoning #Innovation #DrugDiscovery #BusinessStrategy #Research

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A