arXiv AI October 9, 2026 By Bingfan Zeng, Zhisheng Chen, Chenbo Sang, Zhengwei Xie, Jinpeng Wang, Xiangchen Guan, Rui Qian, Zheng Lu, Jingwei Song

MemoWM: How World Models Change What Agents Need to Remember

Read the original on arXiv AI →

MemoWM proposes a memory allocation framework that leverages world models to compress what long‑term agents retain. By using shared predictions, it reconstructs omitted content and balances reconstruction error against storage cost, keeping only information that adds downstream value beyond the predictive prior. On five long‑term agent‑memory benchmarks, MemoWM improves average answer accuracy by 42.42% and cuts experience‑specific storage by 53.9% compared to the most storage‑efficient baseline.

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 Machine Learning

Jul 10

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

arXiv:2607. 08032v1 Announce Type: new Abstract: Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions.

By Ashwin Gerard Colaco, Nada Lahjouji

llms agents efficiency benchmarks

Hugging Face Trending Papers

Jul 15

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memories to reflective insight stores, access memory through fixed, hand-designed heuristics.

llms agents reinforcement-learning benchmarks

arXiv AI

Oct 5

DyadMem: A Long-Term Memory Benchmark of How Agents Work with Users

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

llms agents benchmarks

arXiv AI

Jun 30

SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents

arXiv:2606. 28434v1 Announce Type: cross Abstract: Long-horizon software engineering agents often need to manage lengthy and noisy interaction histories under limited context budgets.

By Shuzheng Gao, Wenhao Zeng, Zhaojian Yu, Jianqiao Wangni, Chaozheng Wang, Kai Cai, Shilin He, Michael R. Lyu

agents

arXiv AI

Jul 16

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

arXiv:2607. 13591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.

By Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu, Levina Li, Dong Liu, Xiao Liang, Rui Sun, Yubei Li, Edward Sun, Haozheng Luo, Zhaolu Kang, Aylin Caliskan, Kai-Wei Chang, Ying Nian Wu

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 16

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.

By Yuyao Wang, Zhongjian Zhang, Mo Chi, Kaichi Yu, Yuhan Li, Miao Peng, Bing Tong, Chen Zhang, Yan Zhou, Jia Li

llms agents benchmarks

One email a morning, machine-written

Related stories

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

DyadMem: A Long-Term Memory Benchmark of How Agents Work with Users

SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective