M$^\star$: Every Task Deserves Its Own Memory Harness

arXiv:2604.11811v1 Announce Type: cross Abstract: Large language model agents rely on specialized memory systems to accumulate and reuse knowledge during extended interactions. Recent architectures typically adopt a fixed memory design tailored to specific domains, such as semantic retrieval for conversations or skills reused for coding. However, a memory system optimized for one purpose frequently fails to transfer to others. To address this limitation, we introduce M$^\star$, a method that aut