Long-term memory has become increasingly important for LLM agents that operate across extended interactions and evolving task contexts. Recent memory systems have made past experiences more persistent, compact, and retrievable, but retrieval alone does not ensure that a memory provides valid evidence for the current query.
arXiv:2605.12978v2 Announce Type: replace Abstract: Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolid...
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
The paper introduces the Distributed‑Evidence Paradox, where long‑running LLM agents compress past interactions into persistent memories that may not be fully supported by the interaction history. It defines three key requirements—evidence scope, compositional validity, and admission reliability—and proposes DerivAudit, a framework that checks whether a memory is truly supported by the available history. Experiments on two memory corpora show that expanding the evidence base can recover support for many memories, yet many remain unsupported, and broader evidence alone does not guarantee reliable admission.
arXiv:2608. 03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history.
arXiv:2608. 02515v1 Announce Type: cross Abstract: Long-running assistants and agents consume interaction streams that eventually outgrow the context.
The paper investigates how long‑horizon language model agents encode memory‑management signals before taking actions. By examining hidden states just prior to each action, the authors find that the model already signals the need for compression and recall, independent of context length or interaction progress, and that these signals vary across model depth. They propose the Preaction Memory with Evidence Retrieval (PaMER) framework, which uses state‑guided compression and selective evidence retrieval to reduce context consumption while preserving task performance.
arXiv:2507. 05257v4 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component-memory, encompassing how agents memorize, update, and retrieve long-term information-is under-evaluated due to the lack of benchmarks.
Long-lived AI agents require continuity across interactions, but continuity cannot be obtained by simply extending the prompt window. An agent must preserve useful prior experience, retrieve it selectively, distinguish personal context from external evidence, and revise memory when the underlying situation changes.
arXiv:2607. 12893v1 Announce Type: new Abstract: Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions.
EdgeMem is a new agent-memory method that preserves original interaction turns and organizes them using complementary content, temporal, and episodic cues via a multi‑anchor hypergraph. It performs lightweight local processing, returning source evidence directly and reserving LLM use only for final answer generation. Experiments on LoCoMo and LongMemEval‑S demonstrate strong retrieval and memory‑grounded question answering, with EdgeMem achieving the highest strict‑judge score among seven systems on LoCoMo while requiring no generative‑LLM calls for construction and retrieval.
arXiv:2607. 05794v1 Announce Type: new Abstract: Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a consumer of pre-selected evidence.
UTILMEM is a new diagnostic benchmark that tests how conversational agents use long‑term memory, focusing on reasoning over dense histories, spotting implicitly relevant memories, synthesizing distributed evidence, and resisting interference from similar distractors. It contains 1,717 instances across five domains and evaluates a range of retrieval‑based and memory‑augmented systems. The study shows that strong performance on traditional factual recall does not guarantee effective memory utilization, highlighting a gap between retrieving information and integrating it into coherent, task‑oriented outputs.