EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation

• URL: http://arxiv.org/abs/2605.30961v1
• Date: Fri, 29 May 2026 07:56:31 GMT
• Title: EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation
• Abstract summary: EvoGens recasts scientific idea generation as an evolutionary search over a population of ideas.<n>It substantially enhances exploration capabilities compared to state-of-the-art baselines.
• Score: 7.417687065241744
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating novel research ideas is fundamental to scientific progress. While Large Language Models (LLMs) show promise in assisting this process, existing approaches often exhibit semantic convergence, resulting in limited diversity and novelty. To address this, we introduce EvoGens, an evolution-inspired framework that recasts scientific idea generation as an evolutionary search over a population of ideas. EvoGens iteratively applies rank-based mutation with differentiated retrieval planning to incorporate external knowledge, and semantic-aware crossover to fuse complementary concepts for conceptual reorganization. A lightweight evaluation signal guides the selection process, encouraging sustained exploration while mitigating premature convergence. Extensive experiments demonstrate that EvoGens substantially enhances exploration capabilities compared to state-of-the-art baselines. Specifically, it improves the Novelty from 0.1 to 0.4 and the Diversity from 0.24 to 0.55, while maintaining comparable idea quality under the current automatic evaluation protocol. These findings suggest that evolutionary mechanisms can serve as a useful framework for exploration-oriented research ideation, especially for broadening the novelty and diversity of candidate ideas under a shared automatic evaluation setting.

Related papers

• Self-Evolving Memory for Generative Recommendation [100.15207958893029]
  Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation.<n>Existing evolving strategies, such as continual retraining and distillation-based adaptation, directly update the shared model parameters.<n>We propose a self-evolving memory paradigm for generative recommendation, aiming to enable effective evolution across heterogeneous behavioral patterns.
  arXiv  Detail & Related papers  (2026-09-14T14:00:38Z)
• Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems [52.75919264158643]
  Evolutionary computation (EC) provides a computational basis for feedback-driven discovery.<n>This review introduces evolutionary intelligence (EI) for scientific discovery.<n>EI characterizes scientific AI systems that sustain exploration by linking candidate refinement with experience retention.
  arXiv  Detail & Related papers  (2026-07-10T01:09:38Z)
• EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery [51.25847252305662]
  EvoSci is a multi-agent scientific collaboration framework, which integrates bio-inspired evolution with knowledge graph modeling.<n>By combining collaborative reasoning, shared memory, and evolutionary feedback, EvoSci significantly enhances the coherence and creativity of scientific exploration.
  arXiv  Detail & Related papers  (2026-05-20T04:58:49Z)
• CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery [67.47220507982522]
  Large language model (LLM)-based evolution is a promising approach for openended discovery.<n>We present CORAL, the first framework for autonomous multi-agent evolution on open-ended problems.<n>CORAL replaces rigid control with long-running agents that explore, reflect, and collaborate.
  arXiv  Detail & Related papers  (2026-04-02T05:59:06Z)
• FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration [27.617408084179246]
  FlowPIE treats literature exploration and idea generation as a co-evolving process.<n>We show that FlowPIE consistently produces ideas with higher novelty, feasibility and diversity.
  arXiv  Detail & Related papers  (2026-03-31T10:37:47Z)
• EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning [15.169565493841384]
  EvoIdeator is a framework that facilitates the evolution of scientific ideas by aligning the RL training objective with textbfchecklist-grounded feedback<n>EvoIdeator, built on Qwen3-4B, significantly outperforms much larger frontier models across key scientific metrics.
  arXiv  Detail & Related papers  (2026-03-23T09:15:26Z)
• Evolutionary Computation as Natural Generative AI [35.99576885880116]
  Evolutionary Computation (EC) offers a search-driven pathway to greater diversity and creativity.<n>EC is a generative paradigm governed by exploratory search under natural selection.<n>We emphasize structured disruption and selection pressure moderation as essential drivers of creativity.
  arXiv  Detail & Related papers  (2025-10-04T01:54:31Z)
• Towards an AI co-scientist [48.11351101913404]
  We introduce an AI co-scientist, a multi-agent system built on Gemini 2.0.<n>The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses.<n>The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method.
  arXiv  Detail & Related papers  (2025-02-26T06:17:13Z)
• On Evolvability and Behavior Landscapes in Neuroevolutionary Divergent Search [0.0]
  Evolvability refers to the ability of an individual genotype to produce offspring with mutually diverse phenotypes. Recent research has demonstrated that divergent search methods promote evolvability by implicitly creating selective pressure for it. This paper provides a novel perspective on the relationship between neuroevolutionary divergent search and evolvability.
  arXiv  Detail & Related papers  (2023-06-16T13:46:55Z)
• Phylogeny-informed fitness estimation [58.720142291102135]
  We propose phylogeny-informed fitness estimation, which exploits a population's phylogeny to estimate fitness evaluations. Our results indicate that phylogeny-informed fitness estimation can mitigate the drawbacks of down-sampled lexicase. This work serves as an initial step toward improving evolutionary algorithms by exploiting runtime phylogenetic analysis.
  arXiv  Detail & Related papers  (2023-06-06T19:05:01Z)
• Epigenetic evolution of deep convolutional models [81.21462458089142]
  We build upon a previously proposed neuroevolution framework to evolve deep convolutional models. We propose a convolutional layer layout which allows kernels of different shapes and sizes to coexist within the same layer. The proposed layout enables the size and shape of individual kernels within a convolutional layer to be evolved with a corresponding new mutation operator.
  arXiv  Detail & Related papers  (2021-04-12T12:45:16Z)
• Complexity-based speciation and genotype representation for neuroevolution [81.21462458089142]
  This paper introduces a speciation principle for neuroevolution where evolving networks are grouped into species based on the number of hidden neurons. The proposed speciation principle is employed in several techniques designed to promote and preserve diversity within species and in the ecosystem as a whole.
  arXiv  Detail & Related papers  (2020-10-11T06:26:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.