arXiv:2604. 11811v3 Announce Type: replace-cross Abstract: Large language model agents rely on a memory harness to write, organize, retrieve, and use past experience.
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 Machine Learning.
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
TrawMem redefines agent memory systems as Task‑Oriented Role‑Adaptive Workspaces, selecting and organizing memories by their roles in task solving rather than mere relevance. It structures interaction histories into local threads and jointly selects complementary memories to build task‑specific workspaces. Experiments on LoCoMo and MemGallery show consistent macro‑F1 gains of 2.23–3.14 points and improved LLM‑Judge scores with fewer context tokens.
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: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...
arXiv:2604.23069v2 Announce Type: replace Abstract: Large language model (LLM) agents often struggle in long-context interactions. As the history grows, sliding windows and prompt compression may dro...
arXiv:2606. 16496v1 Announce Type: cross Abstract: Large multimodal language models (LLMs) have emerged as powerful tools for guiding evolutionary search toward interpretable programmatic policies.