# CMDO: A Cognitive Memory-Driven Optimization Algorithm for Adaptive Population-Based Search

arXiv: https://arxiv.org/abs/2609.35657 · HTML: https://mlsanity.com/paper/2609.35657/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [Recurrent Memory Transformer](https://mlsanity.com/paper/2207.06881/) (2022)
- [Neural Episodic Control](https://mlsanity.com/paper/1703.01988/) (2017)
- [COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting](https://mlsanity.com/paper/1603.08785/) (2016)
- [Episodic Curiosity through Reachability](https://mlsanity.com/paper/1810.02274/) (2018)
- [Model-Free Episodic Control](https://mlsanity.com/paper/1606.04460/) (2016)
- [Generalizable Episodic Memory for Deep Reinforcement Learning](https://mlsanity.com/paper/2103.06469/) (2021)
- [Reviewing and Benchmarking Parameter Control Methods in Differential Evolution](https://mlsanity.com/paper/2010.01035/) (2020)
- [Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognition](https://mlsanity.com/paper/2605.02920/) (2026)
- [Analyzing Adaptive Parameter Landscapes in Parameter Adaptation Methods for Differential Evolution](https://mlsanity.com/paper/2009.12531/) (2020)
- [Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning](https://mlsanity.com/paper/2606.24756/) (2026)
- [Where Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers](https://mlsanity.com/paper/2609.00358/) (2026)

## Abstract (arXiv)

Population-based optimization methods often use previous search information through successful solutions, parameter adaptation, or operator performance, but they rarely retain the context in which a search behavior succeeded or failed. We introduce Cognitive Memory-Driven Optimization (CMDO), a derivative-free population-based optimizer that represents experience as the relationship between search context, search behavior, and observed outcome. CMDO organizes these experiences across working, episodic, and consolidated memory, retrieves them according to similarity with the current search state, and uses both positive and negative evidence to guide subsequent search. Retrieved experience does not replay previous candidate locations; instead, it selects search recipes that are reconstructed from the current population through exploratory, directed, and local search behaviors with adaptive search geometry. We evaluate CMDO on selected Blackbox Optimization Benchmarking test suite on COCO (BBOB/COCO) and Congress on Evolutionary Computation 2017 (CEC2017) problems against DE, CMA-ES, SHADE, GWO, HHO, and ORCA, and further study its application to seven-parameter photovoltaic model estimation using measured current--voltage data. The results show problem-dependent but competitive optimization performance, including the lowest median error among the compared methods on CEC2017 F10. More importantly, analysis of the search traces shows that context-dependent recall changes the distribution of executed search behaviors, while unsuccessful experiences remain available as negative evidence for later decisions, showing that accumulated experience directly influences subsequent search behavior. These results support the use of explicit context--behavior--outcome memory as an active mechanism for controlling population-based search.