The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.
By Shweta Mishra, Shashank Mishra
The paper introduces TriMEM, a multi‑class memory dataset that annotates memory types across varied scenarios, and MemoType, a framework that uses a learned router to adaptively match memories and queries to appropriate retrieval strategies. MemoType’s tailored approach improves retrieval precision, and the authors theoretically show that a single strategy has a fundamental upper bound on expected precision in multi‑class corpora. Experiments on three datasets demonstrate MemoType consistently outperforms existing methods, achieving up to a 16.18% improvement in Recall@1.
By Yi Wen, Derong Xu, Pengyue Jia, Yichao Wang, Yingyi Zhang, Maolin Wang, Junyi Li, Wenlin Zhang, Xiaopeng Li, Yong Liu, Xiangyu Zhao
arXiv:2610.15642v1 Announce Type: new
Abstract: Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively suf...
By Qi Feng, Jicong Fan
arXiv:2608. 20202v1 Announce Type: new Abstract: Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions.
By Mengru Wang, Haozhe Luo, Zhenqian Xu, Zhixiang Cui, Haoming Xu, Qu Yang, Jizhan Fang, Junfeng Fang, Ningyu Zhang
The paper introduces a memory-augmented retrieval method that leverages token-level evidence instead of relying solely on single-vector embeddings. By performing sparse token matching and aggregating scores with whole-memory similarity, the approach improves retrieval performance across eight benchmarks and various model families without extra training. An optional low-rank query adapter can further boost results when supervised.
By Han Luo, Zhan Zhuang, Xu He, Jujia Zhao, Yu Li, Suqin Yuan, Dong Li, Lei Feng
arXiv:2607. 07388v1 Announce Type: cross Abstract: Large Language Models (LLMs) store factual knowledge and domain-specific patterns implicitly in dense Transformer parameters, making knowledge expansion costly through pretraining, fine-tuning, retrieval augmentation, or longer contexts.
By Yutang Ma, Kecheng Huang, Xikun Jiang, Zili Shao
arXiv:2607. 09236v1 Announce Type: new Abstract: Machine unlearning in LLMs is the targeted removal of specific knowledge while preserving all other capabilities, critical for privacy and safety.
By Amit Peleg, Naman Deep Singh, Naama Pearl, Bibhabasu Mohapatra, Matthias Hein
MemCut introduces a benchmark to test user-requested forgetting in large language model agents, featuring 456 hand-designed secrets embedded in long-horizon conversations with fully annotated evidence trails. The benchmark defines two recovery metrics—native and residual—to assess how well secrets can be retrieved after deletion. Experiments across five memory designs and four LLMs show that deletion reduces native recovery more than residual recovery, highlighting candidate coverage as a key bottleneck.
By Cheng Zhang, Xuanning Cao, Zhicheng Zheng, Hui Xiong
arXiv:2609.07093v2 Announce Type: replace
Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely a...
By Yifan Wang, Xinkui Lin, Yongxiu Xu, Shen Gao, Ruochen Yang, Kun Huang, Yubin Wang, Jie Wu, Wei Liu, Jian Luan, Hongbo Xu, Shuo Shang
arXiv:2606.16661v2 Announce Type: replace-cross
Abstract: Fixed-length chunking in Retrieval-Augmented Generation (RAG) often leads to boundary fragmentation, where critical evidence is split across...
By Nathana\"el Langlois
DyadMem introduces a new benchmark for evaluating how long‑term agents remember user‑specific relational information, called User‑conditioned Relational Agent Memory (URAM). The dataset contains 3,065 episodes, 50,961 sessions, and 61,210 QA pairs, with detailed annotations for memory capture, update, and recall across multi‑session trajectories. Experiments on 20 models show strong performance in a gold‑memory setting but a significant drop in full‑pipeline QA, highlighting gaps in current LLM memory capabilities.
By Yifei Tao, Xinyu Zhong, Henry Hengyuan Zhao, Fanyi Wang, Tengda Guo, Wentao Qiu, Ying Wang, Liujian Tang
arXiv:2607. 25600v1 Announce Type: cross Abstract: Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unnecessary computation.
By Chandan Kumar Sah, Xiaoli Lian, Li Zhang