SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents

SEDIMA, a persistent hierarchical insight memory for LLM-driven evolutionary search agents, improves average final performance by 5.5% on AlgoTune and 6.6% on ALE-Bench LITE under a fixed budget of 100 evaluated candidates, according to the arXiv paper 2610.02361v1. SEDIMA distills raw traces into natural-language insights, clusters them by semantic similarity using attention-weighted centroids, and retrieves guidance to condition future mutations, accumulating knowledge across runs. Under OpenEvolve, SEDIMA required 32.3% fewer iterations on average to reach baseline-best performance across five evaluated backbones.

arXiv:2610.02361v1 Announce Type: cross 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.