arXiv:2609.08279v1 Announce Type: cross
Abstract: Agent memory systems must discard stored information when their history exceeds a fixed token budget. Existing budget-accuracy frontiers quantify the...
By Chen Shen
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
arXiv:2609.22231v1 Announce Type: new
Abstract: Long-horizon interactions with LLM-based assistants require memory systems that preserve and update user states, preferences, and interaction histories...
By Zeyu Liu, Jian Zhong, Rongduo Han, Ziyang Wu, Shunye Tang, Chenghao He, Yaxuan Yang, Yihang Qiu, Ailing Wang, Xiao Liang, Guohuan Xie, Xiaokang Xue, Gongchen Li, Haining Zhang, Wei Wang
arXiv:2609.16073v1 Announce Type: cross
Abstract: Retrieval-Augmented Generation (RAG) serves as the primary memory architecture for long-horizon autonomous agents. However, treating shared memory as...
By Hamed HaddadPajouh, Amir AmiriTabat
The paper critiques current agent memory benchmarks that rely on downstream QA accuracy, arguing they conflate memory correctness with retrieval and generation quality, leading to misleading results. It introduces FEB-30, a new benchmark of 30 fact‑evolution trajectories across six diagnostic categories and three difficulty levels, generated automatically to provide deterministic ground truth. Using FEB-30, the authors show a significant divergence between intrinsic and extrinsic evaluations, revealing that a representative memory system correctly classifies memory operations only 20% of the time—an error invisible to traditional QA metrics.
By Sebastian-Antonio Toma, Jean de Kernier, Mike Ply, Oliviu Matei
The paper introduces Experience Memory Graph (EMG), a framework that transforms agent failure recovery into a graph matching problem. By converting failed and successful trajectories into directed action decision graphs, EMG extracts common subgraphs and edit paths that reveal explicit correction strategies, storing them in a memory graph with intra‑task nodes and cross‑task edges. During testing, EMG retrieves relevant insights to guide the agent in a single attempt, improving performance on ALFWorld and ScienceWorld without extra reflection rounds.
By Wenjun Wang, Yuchen Fang, Fengrui Liu, Zibo Liang, Kai Zheng