Abstract
Large language model (LLM)-driven evolutionary search is a powerful paradigm for automated program and algorithm discovery, yet existing systems are largely memoryless: each run explores from scratch, so agents repeatedly rediscover the same improvements and re-encounter the same dead ends. We introduce SEDIMA, a persistent hierarchical insight memory for evolutionary search agents. SEDIMA distills raw traces into natural-language insights, clusters them by semantic similarity using attention-weighted centroids, and retrieves relevant guidance to condition future mutations, accumulating transferable knowledge across runs and problems rather than within a single trajectory. As a drop-in module that leaves the search operators unmodified, SEDIMA improves average final performance by 5.5% on AlgoTune and 6.6% on ALE-Bench LITE under a fixed budget of 100 evaluated candidates. Under OpenEvolve, SEDIMA requires 32.3% fewer iterations on average to reach baseline-best performance across the five evaluated backbones.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Abaskohi, A., Mostajabdaveh, M., & Zhou, Z. (2026). SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents. https://omanscience.com/en/articles/sedima-cross-run-hierarchical-insight-memory-for-evolutionary-search-agents
MLA 9
Abaskohi, Amirhossein, et al. "SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents." https://omanscience.com/en/articles/sedima-cross-run-hierarchical-insight-memory-for-evolutionary-search-agents.
Chicago (author–date)
Abaskohi, Amirhossein, Mahdi Mostajabdaveh, and Zirui Zhou. 2026. "SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents." https://omanscience.com/en/articles/sedima-cross-run-hierarchical-insight-memory-for-evolutionary-search-agents.
Harvard
Abaskohi, A., Mostajabdaveh, M. and Zhou, Z. (2026) 'SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents', Available at: https://omanscience.com/en/articles/sedima-cross-run-hierarchical-insight-memory-for-evolutionary-search-agents.
Vancouver
Abaskohi A, Mostajabdaveh M, Zhou Z. SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents. https://omanscience.com/en/articles/sedima-cross-run-hierarchical-insight-memory-for-evolutionary-search-agents
IEEE
A. Abaskohi, M. Mostajabdaveh, and Z. Zhou, "SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents," https://omanscience.com/en/articles/sedima-cross-run-hierarchical-insight-memory-for-evolutionary-search-agents.