Guiding Evolution of Artificial Life Using Vision-Language Models

• URL: http://arxiv.org/abs/2509.22447v1
• Date: Fri, 26 Sep 2025 15:03:24 GMT
• Title: Guiding Evolution of Artificial Life Using Vision-Language Models
• Authors: Nikhil Baid, Hannah Erlebach, Paul Hellegouarch, Frederico Wieser,
• Abstract summary: We introduce ASAL++, a method for open-ended-like search guided by multimodal Foundation models (FMs)<n>We use a second FM to propose new evolutionary targets based on a simulation's visual history.<n>We explore two strategies: (1) evolving a simulation to match a single new prompt at each iteration (Evolved Supervised Targets: EST) and (2) evolving a simulation to match the entire sequence of generated prompts (Evolved Temporal Targets: ETT)
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundation models (FMs) have recently opened up new frontiers in the field of artificial life (ALife) by providing powerful tools to automate search through ALife simulations. Previous work aligns ALife simulations with natural language target prompts using vision-language models (VLMs). We build on Automated Search for Artificial Life (ASAL) by introducing ASAL++, a method for open-ended-like search guided by multimodal FMs. We use a second FM to propose new evolutionary targets based on a simulation's visual history. This induces an evolutionary trajectory with increasingly complex targets. We explore two strategies: (1) evolving a simulation to match a single new prompt at each iteration (Evolved Supervised Targets: EST) and (2) evolving a simulation to match the entire sequence of generated prompts (Evolved Temporal Targets: ETT). We test our method empirically in the Lenia substrate using Gemma-3 to propose evolutionary targets, and show that EST promotes greater visual novelty, while ETT fosters more coherent and interpretable evolutionary sequences. Our results suggest that ASAL++ points towards new directions for FM-driven ALife discovery with open-ended characteristics.

Related papers

• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• Dyna-Mind: Learning to Simulate from Experience for Better AI Agents [62.21219817256246]
  We argue that current AI agents need ''vicarious trial and error'' - the capacity to mentally simulate alternative futures before acting.<n>We introduce Dyna-Mind, a two-stage training framework that explicitly teaches (V)LM agents to integrate such simulation into their reasoning.
  arXiv  Detail & Related papers  (2025-10-10T17:30:18Z)
• Automating the Search for Artificial Life with Foundation Models [38.43059334611231]
  This paper presents, for the first time, a successful realization of this opportunity using vision-language foundation models.<n>The proposed approach, called Automated Search for Artificial Life (ASAL), finds simulations that produce target phenomena.<n>ASAL works effectively across a diverse range of ALife substrates including Boids, Particle Life, Game of Life, Lenia, and Neural Cellular Automata.
  arXiv  Detail & Related papers  (2024-12-23T18:57:00Z)
• From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models [18.888208951616008]
  Large Language Models (LLMs) have taken the field of AI by storm, but their adoption in the field of Artificial Life (ALife) has been, so far, relatively reserved. We explore the potential of LLMs as tools for ALife research, for example, as operators for evolutionary or the generation of open-ended environments.
  arXiv  Detail & Related papers  (2024-06-14T07:45:32Z)
• A Survey on Self-Evolution of Large Language Models [116.54238664264928]
  Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications. To address this issue, self-evolution approaches that enable LLMs to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing.
  arXiv  Detail & Related papers  (2024-04-22T17:43:23Z)
• Octopus: Embodied Vision-Language Programmer from Environmental Feedback [58.04529328728999]
  Embodied vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. To bridge this gap, we introduce Octopus, an embodied vision-language programmer that uses executable code generation as a medium to connect planning and manipulation. Octopus is designed to 1) proficiently comprehend an agent's visual and textual task objectives, 2) formulate intricate action sequences, and 3) generate executable code.
  arXiv  Detail & Related papers  (2023-10-12T17:59:58Z)
• SELF: Self-Evolution with Language Feedback [68.6673019284853]
  'SELF' (Self-Evolution with Language Feedback) is a novel approach to advance large language models. It enables LLMs to self-improve through self-reflection, akin to human learning processes. Our experiments in mathematics and general tasks demonstrate that SELF can enhance the capabilities of LLMs without human intervention.
  arXiv  Detail & Related papers  (2023-10-01T00:52:24Z)
• Towards Large-Scale Simulations of Open-Ended Evolution in Continuous Cellular Automata [0.0]
  We build large-scale evolutionary simulations using parallel computing framework JAX. We report a number of system design choices, including implicit implementation of genetic operators. We propose several factors that may further facilitate open-ended evolution.
  arXiv  Detail & Related papers  (2023-04-12T06:40:11Z)
• Continual Visual Reinforcement Learning with A Life-Long World Model [55.05017177980985]
  We present a new continual learning approach for visual dynamics modeling.<n>We first introduce the life-long world model, which learns task-specific latent dynamics.<n>Then, we address the value estimation challenge for previous tasks with the exploratory-conservative behavior learning approach.
  arXiv  Detail & Related papers  (2023-03-12T05:08:03Z)

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.