The paper investigates whether artificial evolution can replicate biological neuromodulation and diverse neuron types in indirectly encoded substrates. Experiments show that neuromodulation alone cannot overcome a 75% performance ceiling on parity tasks, but combining neuromodulation with per‑task activation function selection allows a single evolving genotype to achieve 100% success across five tasks. This demonstrates that both neuromodulation and evolvable computational primitives are necessary for multi‑behavioral open‑ended evolution.
By Romain Claret, Michael O'Neill, Paul Cotofrei, Kilian Stoffel
The paper demonstrates that using a single activation function across all nodes in artificial neural networks imposes hard limits on evolutionary search, particularly for sparse evolved substrates. By evolving per-node activation functions from an 18-function palette, the authors show that oscillatory functions can solve parity problems at all tested scales, while monotonic functions fail beyond the simplest case. The study reveals that the choice of activation functions, beyond topology and weights, critically influences what evolutionary search can achieve, and that heterogeneous assignments discovered via indirect encoding are unlikely to be selected manually.
By Romain Claret, Michael O'Neill, Paul Cotofrei, Kilian Stoffel
arXiv:2609.17067v1 Announce Type: cross
Abstract: Indirectly encoded neural networks can assign different activation functions to individual nodes, but the right functions are rarely known in advance...
By Romain Claret, Michael O'Neill, Paul Cotofrei, Kilian Stoffel
EvoTreeNAD is a genealogy‑guided evolutionary algorithm that autonomously discovers neural architectures without a predefined seed or search space. Starting from an empty root, it builds a persistent genealogy where each node represents a complete architecture; top‑percentile values from nodes and descendants steer lineage selection. The method combines an Idea Agent that proposes variants and a Code Agent that implements them, with theoretical analysis showing stationary variation regimes and empirical results demonstrating superior performance on CIFAR‑10/100 and MedMNIST‑v2 tasks.
By Lishan Yu, Derek Jiu, Qizhen Lan, Xiaoqian Jiang
arXiv:2606. 09902v1 Announce Type: cross Abstract: Reservoir computing exploits the fixed dynamics of a recurrent network for temporal processing, requiring only a trained linear readout.
By Anmol Guragain, Savvas Kakalis, Juan Ignacio Godino-Llorente
arXiv:2606. 07664v1 Announce Type: cross Abstract: Neuroevolution is a representative neural architecture search paradigm that evolves both network topology and weights through evolutionary algorithms.
By Wenxiao Li, Yongjian Liu, Qing Xie
arXiv:2607. 04240v1 Announce Type: new Abstract: The transition of Large Language Models (LLMs) from passive generators to autonomous agents has introduced significant challenges in reliability, security, and state management.
By Bogdan Banu
Meta-Reflective Evolution Effectively Improves Production AI Systems describes CoCoEvolve, an evolutionary optimizer that uses meta-reflection to retrieve evidence from the entire evolutionary history and probe live systems before proposing mutations. The approach is applied to data agents, LLM-powered data pipelines, and data engineering workflows, achieving state‑of‑the‑art results on DABStep, multiple LLM pipeline workloads, and data-eng-bench. Ablation studies confirm that each component of CoCoEvolve contributes to its performance gains.
By Seung Won Wilson Yoo, Chang Zeng, Aditi Somayajula, Sahithi Ankireddy, Rohan Kosalge, Avishree Khare, John Mitchell, Aditya G. Parameswaran, Rajhans Samdani, Anupam Datta
arXiv:2607. 11913v1 Announce Type: cross Abstract: Recent advancements in agentic AI have increasingly moved toward graph-based methods, driven by the demand for explainable, human-centered, and non-linear reasoning workflows.
By Ali Kohan, Mohamad Roshanzamir, Roohallah Alizadehsani, Seyedali Mirjalili
arXiv:2609.00129v1 Announce Type: cross
Abstract: The performance of artificial intelligence (AI) and machine learning (ML) models degrades when the problem they were trained on drifts. This is a nea...
By J. M. Diederik Kruijssen (Allora Foundation)
arXiv:2608. 10323v1 Announce Type: new Abstract: Competitive artificial-life systems can rank trained controllers differently under training and ecological evaluation.
By Yuxu Ge, Yifei Cheng
arXiv:2507. 08920v4 Announce Type: replace-cross Abstract: We introduce AMix-1, a powerful protein foundation model built on Bayesian Flow Networks and empowered by a systematic training methodology, encompassing pretraining scaling laws, emergent capability analysis, in-context learning mechanism, and test-time scaling algorithm.
By Changze Lv, Jiang Zhou, Siyu Long, Lihao Wang, Jiangtao Feng, Dongyu Xue, Yu Pei, Hao Wang, Zherui Zhang, Yuchen Cai, Zhiqiang Gao, Ziyuan Ma, Jiakai Hu, Chaochen Gao, Jingjing Gong, Yuxuan Song, Shuyi Zhang, Xiaoqing Zheng, Deyi Xiong, Lei Bai, Wanli Ouyang, Ya-Qin Zhang, Wei-Ying Ma, Bowen Zhou, Hao Zhou