{"ID":2922026,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T08:44:59.422964516Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.00619","arxiv_id":"2606.00619","title":"MemPro: Agentic Memory Systems as Evolvable Programs","abstract":"Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond finite context windows. Existing agentic memory systems typically follow a memory construction-retrieval (MCR) pipeline, but often adapt mainly the memory bank while keeping the surrounding pipeline fixed after deployment. This fixed-pipeline design struggles to handle heterogeneous task-specific failure modes and can become misaligned with memory banks that evolve in scale and structure over time. To address these limitations, we propose MemPro, a system-level evolution framework that treats the entire MCR pipeline as an evolvable program rather than adapting only the memory bank or prompt text. MemPro maintains a version tree of runnable memory-system implementations, where an Evolving Agent iteratively selects promising versions, diagnoses recurring failures, and creates improved child versions through failure-mode-guided edit-debug refinement. Experiments on LongMemEval, LoCoMo, HotpotQA, and NarrativeQA show that MemPro consistently outperforms strong static and prompt-level evolving baselines within a few iterations, continues to improve with evolution, and achieves a favorable performance-cost trade-off. Code is available at https://github.com/wanghai673/MemPro.","short_abstract":"Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond finite context windows. Existing agentic memory systems typically follow a memory construction-retrieval (MCR) pipeline, but often adapt mainly the memory bank while keeping...","url_abs":"https://arxiv.org/abs/2606.00619","url_pdf":"https://arxiv.org/pdf/2606.00619v1","authors":"[\"Qingshan Liu\",\"Guoqing Wang\",\"Wen Wu\",\"Jingqi Huang\",\"Xinqi Tao\",\"Dejia Song\",\"Jie Zhou\",\"Liang He\"]","published":"2026-05-30T08:47:33Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":612632,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T02:42:49.606572591Z","DeletedAt":null,"paper_id":2922026,"paper_url":"https://arxiv.org/abs/2606.00619","paper_title":"MemPro: Agentic Memory Systems as Evolvable Programs","repo_url":"https://github.com/wanghai673/MemPro","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}