arXiv:2603. 00026v2 Announce Type: replace-cross Abstract: Memory management is essential for LLM agents in long-term interactions.
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.
arXiv:2605. 12213v2 Announce Type: replace Abstract: LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context.
arXiv:2606. 06036v1 Announce Type: new Abstract: Despite recent progress, LLM agents still struggle with reasoning over long interaction histories.
RuleMem is a rule-based memory framework designed for long-term conversational agents. It generates natural-language Horn clauses from dialogue histories and validates them with a Rule Perplexity Consistency mechanism, enabling active guidance of evidence retrieval and reasoning. In evaluations on LoCoMo and LongMemEval_s*, RuleMem outperformed 14 baselines, achieving the highest accuracy on LoCoMo with a 27.47‑point absolute gain (54.3% relative improvement).
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.
The paper introduces AMA, a framework that uses multiple agents—Constructor, Retriever, Judge, and Refresher—to manage memory for large language model agents. AMA’s hierarchical memory design dynamically adjusts retrieval granularity to match task complexity, while the Judge and Refresher ensure relevance, consistency, and timely updates. Experiments on long-context benchmarks show AMA outperforms existing baselines and cuts token usage by about 80% compared to full-context approaches.
arXiv:2606. 28349v1 Announce Type: cross Abstract: Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and accumulated interaction histories.