Evolving Semantic and Procedural Memory from Shared Experience for LLM Agents

LLM agents need persistent memory that keeps factual knowledge current and develops reusable procedures from experience. Factual revision and procedural learning require distinct evidence. Coordinating these updates requires a shared context that connects factual knowledge with the experience underlying reusable procedures. We propose Self-Evolving Experience Memory (SEEM${}^2$), an architecture that evolves semantic and procedural memory from shared experience scenes that record context, goals, actions, and outcomes while preserving links to source evidence. Semantic updates revise scoped factual states using new observations while retaining history and unresolved conflicts. Procedural updates learn and refine reusable steps from successful traces, while failures inform applicability conditions and reuse eligibility. Retrieved memories and their supporting evidence guide subsequent tasks, whose observations and outcomes drive further updates with model parameters fixed. Compared with the strongest evaluated baselines, SEEM${}^2$ improves accuracy from 67.67% to 79.33% on the MemoryAgentBench variant of LongMemEval and from 75.48% to 92.90% on BFCL V4 Memory. On the $\tau$-bench family, overall task success increases from 90.65% to 93.17% with DeepSeek-V4-Flash and from 74.46% to 80.22% with Qwen3.8-27B. In a matched Qwen3.8-27B comparison, continued memory updates achieve 81.53% success versus 74.32% with frozen memory, supporting the benefit of ongoing memory evolution.