# Reinforcing Agentic Creativity in Scientific Ideation with Night Science

arXiv: https://arxiv.org/abs/2609.35706 · HTML: https://mlsanity.com/paper/2609.35706/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 53 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 25 of 25)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Reinforcement Learning for Reasoning in Large Language Models with One Training Example](https://mlsanity.com/paper/2504.20571/) (2025)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning](https://mlsanity.com/paper/2505.15134/) (2025)
- [Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation](https://mlsanity.com/paper/2308.10335/) (2023)
- [LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play](https://mlsanity.com/paper/2405.06373/) (2024)
- [We're Different, We're the Same: Creative Homogeneity Across LLMs](https://mlsanity.com/paper/2501.19361/) (2025)
- [Assessing and Understanding Creativity in Large Language Models](https://mlsanity.com/paper/2401.12491/) (2024)
- [AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise](https://mlsanity.com/paper/2507.00310/) (2025)
- [Cognitive Foundations for Reasoning and Their Manifestation in LLMs](https://mlsanity.com/paper/2511.16660/) (2025)
- [Sparks of Science: Hypothesis Generation Using Structured Paper Data](https://mlsanity.com/paper/2504.12976/) (2025)
- [All That Glitters is Not Novel: Plagiarism in AI Generated Research](https://mlsanity.com/paper/2502.16487/) (2025)
- [LLMs can Realize Combinatorial Creativity: Generating Creative Ideas via LLMs for Scientific Research](https://mlsanity.com/paper/2412.14141/) (2024)
- [Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback](https://mlsanity.com/paper/2508.10795/) (2025)
- [AI Can Learn Scientific Taste](https://mlsanity.com/paper/2603.14473/) (2026)
- [Measuring the Gap Between Human and LLM Research Ideas](https://mlsanity.com/paper/2607.01233/) (2026)
- [GIANTS: Generative Insight Anticipation from Scientific Literature](https://mlsanity.com/paper/2604.09793/) (2026)
- [Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis](https://mlsanity.com/paper/2502.14767/) (2025)
- [Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration](https://mlsanity.com/paper/2603.12226/) (2026)
- [Beyond True or False: Retrieval-Augmented Hierarchical Analysis of Nuanced Claims](https://mlsanity.com/paper/2506.10728/) (2025)
- [Are LLMs becoming similarly creative? Evidence from three years of models](https://mlsanity.com/paper/2608.19437/) (2026)

## Abstract (arXiv)

Large language models (LLMs) excel at structured, verifiable tasks, but their low-entropy bias can produce homogeneous and predictable outputs, limiting their utility for open-ended scientific ideation. Effective discovery, however, spans a broader creative spectrum: from structured day science to loosely structured, serendipitous night science that reaches ideas beyond those typically considered. We introduce AI Night-Scientist, an agentic framework that uses reinforcement learning to teach models when and how to depart from predictable reasoning. Grounded in cognitive science, we model creativity along three axes: action (what to do and how creatively), process (when to explore versus exploit), and outcome (the novelty and usefulness of the resulting idea). We use these axes to train models with GRPO, exposing them to varying degrees and forms of creativity throughout training. This produces substantially more diverse scientific proposals, expanding the range of research directions by 27.8% and contribution types by 14.9% over the base model. It also improves predicted citation impact by up to 32.0 percentage points and originality by 66.2 points. These gains cannot be reproduced by simply increasing decoding temperature; instead, we find that semantic guidance specifying what kind of creativity to pursue is critical. Overall, our results suggest that creativity is a learnable, multi-level ability that can be shaped to help researchers reach ideas beyond those typically explored by LLMs.