Identifying potentiating events in evolutionary search using replay experiments

• URL: http://arxiv.org/abs/2608.09833v1
• Date: Mon, 10 Aug 2026 16:50:41 GMT
• Title: Identifying potentiating events in evolutionary search using replay experiments
• Abstract summary: We give a step-by-step guide to designing replay experiments for evolutionary computing systems.<n>We argue that analytical replay experiments can be a powerful tool for expanding the theoretical foundations of evolutionary computing.
• Score: 46.00263113357165
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we introduce analytical replay experiments to the evolutionary computing community. Replay experiments originated in the context of laboratory experimental evolution as an empirical approach to identifying potentiating events that increased the likelihood of an observed evolutionary outcome. By restarting a population's evolution from different historical time points, replay experiments sample the distribution of what could have evolved from different points in time, which allows us to quantify how a population's potential for different evolutionary outcomes changed as a result of that population's history. In this work, we give a step-by-step guide to designing replay experiments for evolutionary computing systems. We then provide a demonstrative example replay experiment that measures how potentiation for problem-solving success changed in an evolved genetic programming population, showing that increases in potential for success do not necessarily correspond with increases in a population's fitness. Broadly, we argue that analytical replay experiments can be a powerful tool for expanding the theoretical foundations of evolutionary computing, and we offer suggestions for promising future research directions enabled by replay experiments.

Related papers

• 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)
• EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation [7.417687065241744]
  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.
  arXiv  Detail & Related papers  (2026-05-29T07:56:31Z)
• CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad [72.197582948888]
  We develop CausalEvolve, equipped with a causal scratchpad that leverages Large Language Models (LLMs) to identify and reason about guiding factors for evolution.<n>CaulEvolve first identifies outcome-level factors that offer complementary inspirations in improving the target objective.<n>During the evolution, CausalEvolve also inspects surprise patterns during the evolution and abductive reasoning to hypothesize new factors, which in turn offer novel directions.
  arXiv  Detail & Related papers  (2026-03-15T19:53:31Z)
• FLEX: Continuous Agent Evolution via Forward Learning from Experience [54.796367711967754]
  Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training.<n>We introduce Forward Learning with EXperience (FLEX), a gradient-free learning paradigm that enables LLM agents to continuously evolve through accumulated experience.
  arXiv  Detail & Related papers  (2025-11-09T16:31:39Z)
• Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents [58.69865074060139]
  We study the case where an agent's self-evolution deviates in unintended ways, leading to undesirable or even harmful outcomes.<n>Our empirical findings reveal that misevolution is a widespread risk, affecting agents built even on top-tier LLMs.<n>We discuss potential mitigation strategies to inspire further research on building safer and more trustworthy self-evolving agents.
  arXiv  Detail & Related papers  (2025-09-30T14:55:55Z)
• MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback [136.27567671480156]
  We introduce experiment-guided ranking, which prioritizes hypotheses based on feedback from prior tests.<n>We frame experiment-guided ranking as a sequential decision-making problem.<n>Our approach significantly outperforms pre-experiment baselines and strong ablations.
  arXiv  Detail & Related papers  (2025-05-23T13:24:50Z)
• Evolutionary Prediction Games [14.771178412529856]
  We introduce evolutionary prediction games, a framework grounded in evolutionary game theory.<n>In idealized settings with unlimited data and computational power, repeated learning creates competition and promotes competitive exclusion.<n>We show that stable coexistence and mutualistic symbiosis between groups becomes possible under realistic constraints.
  arXiv  Detail & Related papers  (2025-03-05T11:24:55Z)
• Evolving choice hysteresis in reinforcement learning: comparing the adaptive value of positivity bias and gradual perseveration [0.0]
  We show that positivity bias is evolutionary stable in many situations, while the emergence of gradual perseveration is less systematic and robust. Our results illustrate that biases can be adaptive and selected by evolution, in an environment-specific manner.
  arXiv  Detail & Related papers  (2024-10-25T09:47:31Z)
• Phylotrack: C++ and Python libraries for in silico phylogenetic tracking [0.0]
  The Phylotrack project provides libraries for tracking and analyzing phylogenies in in silico evolution. The project is composed of 1) Phylotracklib: a header-only C++ library, developed under the umbrella of the Empirical project, and 2) Phylotrackpy: a Python wrapper around Phylotracklib, created with Pybind11.
  arXiv  Detail & Related papers  (2024-05-15T14:47:43Z)
• 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)
• Mimicking Evolution with Reinforcement Learning [10.35437633064506]
  We argue that the path to developing artificial human-like-intelligence will pass through mimicking the evolutionary process in a nature-like simulation. This work proposes Evolution via Evolutionary Reward (EvER) that allows learning to single-handedly drive the search for policies with increasingly evolutionary fitness.
  arXiv  Detail & Related papers  (2020-03-31T18:16:53Z)

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.