Evolutionary Algorithm for Reservoir Learning and Yielding
Summary
Introduces EARLY, an evolutionary framework for evolving multi-reservoir Echo State Networks that outperforms random search on temporal learning tasks and exhibits task-dependent structural differences.
View Cached Full Text
Cached at: 06/01/26, 09:29 AM
# Evolutionary Algorithm for Reservoir Learning and Yielding Source: [https://arxiv.org/abs/2605.30372](https://arxiv.org/abs/2605.30372) [View PDF](https://arxiv.org/pdf/2605.30372) > Abstract:Reservoir computing, a type of recurrent neural network, is a promising approach for temporal learning as it separates dynamic processing from the trained readout layer\. However, classical Echo State Networks \(ESNs\) often require task\-specific tuning of their architecture and hyperparameters to achieve good performance\. This paper introduces EARLY \(Evolutionary Algorithm for Reservoir Learning and Yielding\), a framework designed to evolve both the topology and hyperparameters of multi\-reservoir ESNs\. Inspired by the modular organisation of the brain, EARLY encodes architectures as graph\-based genomes and applies crossover, mutation, and selection to discover effective configurations\. Our goal is to create both generic architectures and tasks inducing generalization\. The method is evaluated on temporal learning tasks from the CogScale dataset\. Results show that evolved architectures outperform those obtained with random search on several tasks and exhibit structural differences depending on task difficulty: simpler tasks yield lightweight architectures, while more complex tasks favour richer modular organisations\. These findings suggest that evolutionary search can help identify reusable reservoir structures for a broader range of temporal problems\. The evolved architectures are further evaluated on a cross\-situational learning dataset to assess their ability to adapt to new environments\. ## Submission history From: Julien Testu \[[view email](https://arxiv.org/show-email/a4cf769c/2605.30372)\] \[via CCSD proxy\] **\[v1\]**Tue, 19 May 2026 11:22:21 UTC \(4,592 KB\)
Similar Articles
Recursive Self-Evolving Agents via Held-Out Selection
Introduces RSEA, a method for recursive self-evolution of LLM agents using a three-layer natural-language state and a held-out selection gate to prevent regression. Evaluated across four benchmarks, it shows that context evolution is benchmark-dependent and that a strict selection gate is crucial for reliability.
ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
Introduces ERSkill, a retrieval-centric framework for self-evolving, skill-guided adaptive memory access in LLM agents. It co-evolves retrieval skills and a routing policy, substantially outperforming strong baselines across agent memory benchmarks.
Scalable Perturbation Learning for Online Self-Supervised Echo State Networks
Proposes a perturbation-based learning rule for online self-supervised learning in echo state networks that avoids reservoir-size-dependent variance growth by decomposing the learning cost and perturbing only the input-dependent component.
Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging
This paper proposes Hyper-ES, a subspace-based evolution strategy framework for LLM reasoning that obtains descent directions via lightweight gradient-based fine-tuning and then uses CMA-ES to merge layer-wise DARE-TIES coefficients, consistently outperforming GRPO-LoRA while requiring fewer gradient updates.
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
EvoTrainer introduces an autonomous training framework that co-evolves LLM policies and training harnesses through empirical feedback, outperforming human-engineered RL baselines on mathematical reasoning, code generation, and long-horizon software engineering tasks.