arXiv:2606. 00619v1 Announce Type: cross Abstract: Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond finite context windows.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
MemMA is a plug‑and‑play multi‑agent framework that coordinates the memory cycle of memory‑augmented LLM agents on both forward and backward paths. On the forward path, a Meta‑Thinker guides a Memory Manager for construction and a Query Reasoner for iterative retrieval. On the backward path, MemMA performs in‑situ self‑evolving memory construction, generating probe QA pairs, verifying the memory, and converting failures into repair actions before finalization. Experiments on LoCoMo show that MemMA consistently outperforms existing baselines across multiple LLM backbones and improves three different storage backends.
arXiv:2609.39765v1 Announce Type: new Abstract: Agent memory faces heterogeneous access needs: a single-hop question may require one piece of evidence, whereas a multi-hop question must combine evide...
Agent memory faces heterogeneous access needs: a single-hop question may require one piece of evidence, whereas a multi-hop question must combine evidence from multiple sources. Predefined memory work...
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
arXiv:2606. 17546v1 Announce Type: new Abstract: Self-evolving LLM-based agents improve mainly by changing their agent harness: the structured execution layer around a base model, including prompts, memory, tools, middleware, runtime state, and the model-tool interaction loop.
arXiv:2606. 06054v1 Announce Type: new Abstract: Personal AI agents increasingly rely on long-term memory to provide persistent personalization across sessions.