CLAIMay 30

MemPro: Agentic Memory Systems as Evolvable Programs

arXiv:2606.0061998.7h-index: 3Has Code
AI Analysis

For developers of long-horizon autonomous agents, MemPro offers a system-level evolution framework that adapts the entire memory pipeline to handle heterogeneous failure modes and evolving memory banks.

MemPro treats the entire memory construction-retrieval pipeline as an evolvable program, outperforming static and prompt-level evolving baselines on LongMemEval, LoCoMo, HotpotQA, and NarrativeQA within a few iterations.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes