PrivDrift is a benchmark that tests whether user‑disclosed secrets can still be recovered by large language models after the conversation shifts to unrelated topics. It includes 1,000 controlled multi‑turn dialogues with seeded secrets, topic‑drift turns, and standardized extraction probes. Experiments on three LLMs with extended context windows show that dialogue‑level leakage remains substantial—between 38.7% and 54.6%—and is influenced by model, secret type, and persuasion intensity, while additional topic drift does not reliably reduce leakage.
By Luciano Maldonado
The paper introduces AIM, a privacy‑aware memory framework that lets multi‑agent, multi‑user large language models manage both private and shared memory. AIM classifies data as private (user‑specific) or public (shared) and enforces index‑level access controls to protect sensitive information while enabling shared knowledge to improve coordination. The authors also present MUMBench, a new dataset for evaluating memory operations in multi‑user settings, and report high accuracy metrics for AIM on this benchmark.
By Zachary Johnson, Nigel Boachie Kumankumah, Somya Chatterjee, Tejas Sathyamurthi, Min Chen, Xinyi Alice Li, Xiao Wang, Emily Morgan Gelchie, Jessica Lin, Sadid A. Hasan, Sulaiman Vesal
arXiv:2607. 01935v1 Announce Type: new Abstract: Long term memory lets LLM agents act as persistent assistants, but user facts change.
By Zitong Shi, Yixuan Tang, Anthony Kum Hoe Tung
arXiv:2606. 04315v1 Announce Type: new Abstract: LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems.
By Zhikai Chen, Jialiang Gu, Junyu Yin, Xianxuan Long, Shenglai Zeng, Xiaoze Liu, Kai Guo, Keren Zhou, Jiliang Tang
arXiv:2609.23465v1 Announce Type: new
Abstract: Long-horizon conversational memory is especially challenging in multi-actor settings, where relevant evidence is distributed across participants and co...
By Zihao Lu, Zhihang Yuan, Lei Shi
SKILL.state is a new runtime architecture for large language model agents that replaces the traditional append‑only conversational history with an explicit, mutable execution state. At each step the model receives only the immutable skill specification, the current structured state, and the latest observation, discarding intermediate reasoning after validating state updates. Experiments across datasets, models, and environments show that SKILL.state improves task accuracy and significantly reduces cumulative token consumption, proving that explicit execution state is a scalable, architecture‑agnostic abstraction for long‑horizon agent skills.
By Sanket Badhe, Priyanka Tiwari, Jonghyun Chung
Multi-agent large language model (LLM) systems can expose protected state through internal messages, tool arguments, logs, and persistent memory even when their public outputs appear innocuous. Existing privacy prompts, redaction methods, and source-level access controls restrict surface content or data access, but do not specify what a legitimately informed agent should disclose or how that disclosure may be reused downstream.
arXiv:2605. 12213v2 Announce Type: replace Abstract: LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context.
By Jiazhou Liang, Armin Toroghi, Yifan Simon Liu, Faeze Moradi Kalarde, Liam Gallagher, Scott Sanner
arXiv:2607. 04089v1 Announce Type: new Abstract: Lifelong agents need more than larger context windows and better retrieval.
By Sukanta Ganguly
arXiv:2607. 06595v1 Announce Type: cross Abstract: Personal AI agents powered by large language models can reason and act using available tools to access emails, manage calendars, and push code to remote repositories, all with minimal oversight.
By George Torres, Sharad Shrestha, Satyajayant Misra
The paper introduces the Hydration Proxy Pattern, an architectural approach that separates session persistence from the reasoning engine in conversational AI systems. This pattern allows enterprise platforms to maintain sovereignty over conversational data while still leveraging stateless LLM APIs for scalability. Additionally, the authors propose the Context Stabilization Mandate to balance sovereign state management with key‑value caching.
By Joseph Axisa
MemoryArena is a new evaluation gym that benchmarks agent memory in interdependent multi‑session tasks. Unlike prior benchmarks that test memorization or single‑session action in isolation, MemoryArena requires agents to acquire memory while interacting with the environment and then use that memory to guide future decisions across a range of tasks such as web navigation, planning, information search, and formal reasoning. The benchmark reveals that agents excelling on existing long‑context memory tests perform poorly here, highlighting a gap in current memory evaluation methods.
By Zexue He, Yu Wang, Churan Zhi, Yuanzhe Hu, Tzu-Ping Chen, Lang Yin, Ze Chen, Tong Arthur Wu, Siru Ouyang, Zihan Wang, Jiaxin Pei, Julian McAuley, Yejin Choi, Alex Pentland