Associative Constructive Evolution: Enhancing Metaheuristics through Hebbian-Learned Generative Guidance
arXiv:2603.29774v1 Announce Type: new Abstract: Metaheuristic algorithms such as Particle Swarm Optimization (PSO) and Evolutionary Algorithms (EA) excel at exploring solution spaces but lack mechanisms to accumulate and reuse procedural knowledge from successful search trajectories. This paper proposes Associative Constructive Evolution (ACE), a framework that enhances metaheuristics through learned generative guidance. ACE introduces a Generative Construction Automaton (GCA) -- a probabilistic model over operation sequences -- coupled with the base metaheuristic in a synergistic loop: the metaheuristic explores and provides trajectory samples, while the GCA consolidates successful patterns and guides future exploration. Three mechanisms realize this cooperation: Hebbian weight consolidat
View PDF HTML (experimental)
Abstract:Metaheuristic algorithms such as Particle Swarm Optimization (PSO) and Evolutionary Algorithms (EA) excel at exploring solution spaces but lack mechanisms to accumulate and reuse procedural knowledge from successful search trajectories. This paper proposes Associative Constructive Evolution (ACE), a framework that enhances metaheuristics through learned generative guidance. ACE introduces a Generative Construction Automaton (GCA) -- a probabilistic model over operation sequences -- coupled with the base metaheuristic in a synergistic loop: the metaheuristic explores and provides trajectory samples, while the GCA consolidates successful patterns and guides future exploration. Three mechanisms realize this cooperation: Hebbian weight consolidation that strengthens associations between co-successful operations, guided sampling that biases search toward learned high-quality regions, and symbolic abstraction that extracts frequent patterns into reusable macro-operations. Experiments integrating ACE with EA and PSO on molecular design and maze navigation demonstrate consistent improvements. ACE-PSO achieves a 27.5% increase in success rate while reducing convergence time by 49.6%. In molecular design, ACE-EA improves fitness by 10.1% with 126 chemically interpretable macro-operations automatically discovered.
Comments: 4 pages, accepted as a short paper (poster) at GECCO 2026
Subjects:
Neural and Evolutionary Computing (cs.NE)
ACM classes: I.2.8
Cite as: arXiv:2603.29774 [cs.NE]
(or arXiv:2603.29774v1 [cs.NE] for this version)
https://doi.org/10.48550/arXiv.2603.29774
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Shanxian Lin [view email] [v1] Tue, 31 Mar 2026 14:14:40 UTC (126 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
modelannouncepaper
Announcing Doublehaven with Reflections on Humour
Inkhaven is a writers’ retreat, well, really it’s a bloggers’ retreat. In the Lighthaven campus, Berkeley, a couple dozen bloggers get together to complete an almost insurmountable challenge for us mere mortals. Post one blogpost every single day for a whole month. I say ‘insurmountable’ but in fact they all succeeded last time, although apparently it was not uncommon for them to claw success from the jaws of defeat at 11:45 pm each night. I look at this and I feel the same way that traditionalists feel when they see Millennials scared to use the phone, or Gen Zs unable to go outside. Our (blogosphere) ancestors used to blog seventy times per day! Great Yudkowsky used to go to war (with the methods of rationality)! Moldbug and Alexander were gunning each other down (with devastating couter
There Is No Such Thing As a Service
<p>If you have been following this series, you know I am a fan of services. Dependency injection, single responsibility, clean boundaries between concerns. Done right, you end up with hundreds of services, each doing exactly one thing.</p> <p>But here is the problem nobody talks about: the word "service" does not actually mean anything.</p> <p><code>ItemService</code>. What does it do? Everything. What is inside? Who knows. You have to open it and start reading. And the more your codebase grows, the more that class becomes a dumping ground, a god class disguised by a reasonable name.</p> <p>I want to argue that the service as we know it is just one of many distinct types of classes we could be writing. And the moment you start thinking in terms of those types, your code becomes something a
HDF5 vs. TsFile: Efficient Time-Series Data Storage
<p>In the era of big data, efficient data storage and management are critical to the success of both scientific research and industrial applications. <a href="https://www.hdfgroup.org/solutions/hdf5/" rel="noopener noreferrer">HDF5</a>, a hierarchical format for managing experimental data, and <a href="https://tsfile.apache.org" rel="noopener noreferrer">TsFile</a>, a modern time-series data storage format, each offer unique strengths and design philosophies. This article takes a deep dive into the origins, use cases, and limitations of HDF5, and explores the similarities and differences between HDF5 and TsFile.</p> <h2> Origins of HDF5 </h2> <p>HDF5, short for <em>Hierarchical Data Format version 5</em>, is more than just a file format. It encompasses a full data model, software libraries
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Research Papers
Hidden Helpers: Pittsburgh’s Industrial Past Might Hold the Key to a Cleaner Future
<p> <img loading="lazy" src="https://www.cmu.edu/news/sites/default/files/styles/listings_desktop_1x_/public/2026-03/260305B_WTM_Armbruster038.jpg.webp?itok=8RGXrI_N" width="900" height="508" alt="Researchers examine soil"> </p> Pittsburgh has reinvented itself from a steel powerhouse to a hub for health care and education. But the city’s industrial past left a hidden legacy: toxic compounds like benzene and toluene in the soil. While most life can’t survive such a contamination, some microbes adapted to use the pollutants as food.
XR is XR: Rethinking MR and XR as Neutral Umbrella Terms
arXiv:2603.29939v1 Announce Type: new Abstract: The term XR is currently widely used as an expression encompassing Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR). However, there is no clear consensus regarding its origin or meaning. XR is sometimes explained as an abbreviation for Extended Reality, but multiple interpretations exist regarding its etymology and formation process. This paper organizes the historical formation of terminology related to VR, AR, MR, and XR, and reexamines the context in which the term XR emerged and how it has spread. In particular, by presenting a timeline that distinguishes between the coinage of terms and the drivers of their adoption, we suggest that XR, as an umbrella term, functions not as an abbreviation of Extended Reality, but rat
Interview-Informed Generative Agents for Product Discovery: A Validation Study
arXiv:2603.29890v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong performance on standardized social science instruments, but their value for product discovery remains unclear. We investigate whether interview-informed generative agents can simulate user responses in concept testing scenarios. Using in-depth workflow interviews with knowledge workers, we created personalized agents and compared their evaluations of novel AI concepts against the same participants' responses. Our results show that agents are distribution-calibrated but identity-imprecise: they fail to replicate the specific individual they are grounded in, yet approximate population-level response distributions. These findings highlight both the potential and the limits of LLM simulation in desig
Beyond Legacy OFDM: A Mobility-Adaptive Multi-Gear Framework for 6G
arXiv:2603.29721v1 Announce Type: new Abstract: While Third Generation Partnership Project (3GPP) has confirmed orthogonal frequency division multiplexing (OFDM) as the baseline waveform for sixth-generation (6G), its performance is severely compromised in the high-mobility scenarios envisioned for 6G. Building upon the GEARBOX-PHY vision, we present gear-switching OFDM (GS-OFDM): a unified framework in which the base station (BS) adaptively selects among three gears, ranging from legacy OFDM to delay-Doppler domain processing based on the channel mobility conditions experienced by the user equipments (UEs). We illustrate the benefit of adaptive gear switching for communication throughput and, finally, we conclude with an outlook on research challenges and opportunities.
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!