Personal Information Management and User Behavior

Neueste Paper

• The GUI Is Not the State: Diagnosing State Aliasing in GUI World Models

  Dongsheng Liu, Chao Jin, Wenkui Yang, Hejin Wang, Junwei Yang, Zeren Zhang, Ziwei Chen, Huaibo Huang, Jie Cao, Ran He · 29. September 2026

  GUI World Models (GUI-WMs) are increasingly used to predict future states for agent planning and simulation, yet most existing formulations condition only on the current GUI observation and action. We identify state aliasing, where the vis- ible interface omits transition-relevant environment state,…

• On Evaluating and Improving Conversational Agents in Production

  Kasra Hosseini, Wen-Sen Cheng, Marco-Andrea Buchmann, Emir Mulabegovic, Weiwei Cheng · 29. September 2026

  We present a framework for evaluating and improving a large-scale, multi-agent shopping assistant in production, and report lessons from its use. Offline evaluation of such a system faces three obstacles. (i) A logged conversation cannot be replayed against a modified system, because a different res…

• EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents

  Fengzhou Sun, Yuan Zhang, Xintong Yu, Jinyao Yan · 29. September 2026

  Large language model (LLM) agents face critical privacy risks when acting as delegates in human-agent-human communication. To prevent such breaches, agents must understand users' social relationships and adhere to context-dependent social information disclosure boundaries. Current studies on agent m…

• Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses

  Weiyuan Li, Jinghan Xu, Aili Chen, Xintao Wang, Shuang Liang, Jiaqing Liang, Deqing Yang · 29. September 2026

  Harness evolution improves LLM agents by learning from execution trajectories, but existing experience- and skill-based methods are less effective on long-horizon tasks. As interactions grow, useful evidence can be buried by redundant or outdated context, making context management itself a key bottl…

• After the Fix: How Corrected Agent Histories Transfer to Related Tasks

  Yanfei Zhang, Xu Lin · 29. September 2026

  Does repairing an episode make its experience a better memory for the next task? We transfer the same failed source before and after accepted repair to a fixed target, alongside independent execution. Our 3,300 runs cover 100 ThinkingBox pairs and the same 100 APEX pairs with and without source-stat…

• FlowState: Execution State as Memory for Long-Horizon LLM Agents

  Minghao Li, Bangyan Li, Zifan Wang, Yulong Li, Hu Xu, Gan Zhang, Jingtong Wu, Wenqiang Xu · 29. September 2026

  Long-horizon tasks require LLM agents to continually draw on information from earlier interactions. However, retaining the full history increases context costs, while compressing it risks losing details needed later, and the relevance of historical information often becomes apparent as the task prog…

• Remember Before You're Asked: MemDream for Self-Probing Memory Evolution

  Mingfei Lu, Mengjia Wu, Runsong Jia, Zhe Luo, Yi Zhang · 29. September 2026

  Memory is essential for enabling LLM-based agents to maintain coherent, personalized behavior over long-horizon interactions. However, existing memory systems share a fundamental limitation: they never proactively test their own memory, repairing it only after real queries expose weaknesses. This re…

• PairPref: When Should Memory Guide the Answer? A Benchmark for Contextual Preference Use

  Mingfei Lu, Mengjia Wu, Yi Zhang · 29. September 2026

  Memory-augmented assistants use retrieved preferences to guide their responses. A small change in the situation can change whether a preference is appropriate while barely affecting its retrieval similarity. Memory benchmarks typically test whether systems store and retrieve preferences, with less a…

• Stashbird: Efficient Speaker-Indexed Memory for Conversational Agents

  Chidera Biringa, Lucas Yannul, Xiaowen Wang, Marco Ayala, Nicholas Yi, Alex Moyse, Nishant Manchanda, Vivek Gupta · 29. September 2026

  AI agents require memory that preserves information across user-agent exchanges, user-to-user conversations, and group conversations with or without agent participation, while supporting updates as evidence changes or is removed. We present Stashbird, an agent memory system that links source episode…

• ReplayLens: Auditing Agents' Use of Outcomes

  Dong Xu, Zhangfan Yang, Jiantao Wu, Shipeng Zhang, Zexuan Zhu, Jiangqiang Li, Jun Zhang, Junkai Ji · 29. September 2026

  When an agent reuses logged experience, a changed decision may reflect the recorded score, the action's name, or the record's position in storage. Standard memory evaluations do not reveal which relationship drives that change. We introduce ReplayLens, a black-box audit that changes one relationship…

• ActiveMem: Dynamic Latent Memory Trees for Long-Horizon Agents

  Song-Li Wu, Jingyi Wang, Zhaocheng Du, Weinan Gan · 29. September 2026

  Large Language Model (LLM) agents increasingly rely on external memory to support long-horizon reasoning and decision making. Existing memory systems typically retrieve historical trajectories or summaries as independent context fragments, overlooking the procedural dependencies underlying multi-ste…

• AgentHabit: Characterizing Distinct Behaviors of Agents on Everyday Tasks

  Woojung Song, Hoyeol Yang, Jeonghoon Shim, Sungjib Lim, Jonggeun Lee, Yunho Choi, Yohan Jo · 29. September 2026

  Large language model (LLM) agents assist users with everyday tasks that can be completed in many reasonable ways. Even when their answers are useful, how agents carry out these tasks may not match users' preferences and needs. For example, agents differ in whether they ask clarifying questions or se…

• Dude, Where's My State? Execution Information Requirements for Stateful Agents

  Nikita Mehrotra, Ashish Tiwari, Priyanshu Gupta, Sumit Gulwani · 29. September 2026

  Long-running agents must preserve information that later steps depend on. We introduce the Execution Information Requirement (EIR), a lower bound on the information that must remain accessible for correct completion under specified task and access conditions. We develop LACUNA, a framework that gene…

• CUE-Mem: Benchmarking Long-Term User Memory via Implicit Cues in Multimodal Conversations

  Yulin Hu, Yanyan Zhao, Zimo Long, Xing Fu, Mengtong Ji, Weixiang Zhao, Yutai Hou, Qianchao Wang, Dandan Tu · 29. September 2026

  Long-term memory is essential for multimodal agents that interact with users across sustained conversations. However, user memories are not always explicitly stated: they may also be implied by recurring background objects in images, ambient sounds in audio, or other peripheral multimodal cues. Exis…

• Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents

  Jinming Hu, Haodong Zhao, Qi Jia, Die Chen, Tianhang Zhao, Sufeng Duan, Gongshen Liu · 29. September 2026

  Large language model (LLM) agents serving different users often solve related tasks, yet separate user histories can leave reusable experience inaccessible to other agents. Pooling memories expands access but risks transferring preferences that conflict with the receiving user's requirements. We int…

• SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation

  Youngmok Jung, Sirajul Salekin, Henry Tran, Javier Movellan, Zhao Huang, Manjot Bilkhu · 29. September 2026

  Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requires interleaving tasks with agent-side events such as session stop and start, crons, and memory consolidation. Yet existing benchmarks and training fra…

• CoMemBench: Benchmarking Collaborative Memory Boundaries across Multi-Agent Workflow Topologies

  Sen Zhao, Ruiqi Kong, Zuyu Zhang, Lifeng Shen, Xinyu He, Ding Zou, Xu Zhang, Qinghua Zhang · 29. September 2026

  Multi-agent workflows require task-relevant information to be shared across agents, while irrelevant, stale, unverified, or incompatible information must remain isolated. We call this task-conditioned scope of information a collaborative memory boundary. Workflow topology determines which intermedia…

• PastForward: Faster On-Device GUI Agents via Computational Experience Reuse

  Taehwan Park, Changmin Lee, Hayeon Lee, Taesik Gong · 29. September 2026

  Running GUI agents on edge devices can keep sensitive screens and interaction histories local, but the computational cost of inference at every action step makes deployment challenging. Existing GUI agent systems either perform full vision-language model (VLM) inference at each action step or reuse …

• EmailBench: A Benchmark for Evaluating LLM Agents on Enterprise Email and Productivity Tasks

  Mukul Singh, Mansi Uniyal, Devin Devlin, Wen Xie, Big Thadawasin, Ritam Dutt, Vivian Lai, Hyeonsu B. Kang · 29. September 2026

  Enterprise email agents must combine information retrieval, structured state changes, temporal reasoning, and multi-step coordination. Recent agent benchmarks include productivity tasks, but few center on typed email workflows in a self-contained environment. We introduce EmailBench, a benchmark of …

• COUNTERMEM: World-Model Verified Counter-Factual Memory for Language Agents

  Hongji Pu, Ruixiang Tang, Yongfeng Zhang · 29. September 2026

  Existing agent memory frameworks mainly create memory through an agent's interaction with the factual world, e.g., remembering feedback from actions taken to improve performance on future tasks. However, these frameworks seldom ask the "what if" question during memory construction: what if a differe…

• PIA: A Personal Intelligence Agent Turning Health Conversations into Records and Records into Understanding

  Jeonghun Yoon, Dongchan Kim, Hongyeon Yu, Young-Bum Kim, Jaegul Choo · 28. September 2026

  General-purpose agent memory summarizes conversations: it extracts salient snippets, embeds them, and retrieves the top-k into the prompt. A health agent cannot run on summaries: a dose becomes a sentence, "since last week" is resolved at the model's discretion, and a three-month glucose trend canno…

• Not All Memories Are Equal: Hierarchical Collaborative Memory for Validity-Aware Retrieval in LLM Agents

  Yufei Shi, Rujing Yao, Ang Li, Yang Wu, Zhuoren Jiang, Xiaozhong Liu · 28. September 2026

  In team collaboration scenarios, memory is heterogeneous and continually evolving. Team memories capture collective decisions, protocols, and current consensus, while individual memories preserve member-specific observations, execution traces, and intermediate progress. Existing memory-augmented sys…

• The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge

  Alexander Gill, Md Farhan Ishmam, Xuyen Nguyen, Neha Bhat, Parker Henry DeYoung, Fateme Hashemi Chaleshtori, Nathan Stringham, Kenneth Marino, Ana Marasovi\'c · 28. September 2026

  Existing computer-use agent benchmarks do not fully evaluate agents acting as assistants. A useful assistant retrieves information across complex, multi-step workflows, synthesizes it into artifacts (documents, presentations, spreadsheets), and navigates program interfaces to produce a coherent fina…

• Probing Stability-Plasticity Tradeoffs in Agent Memory through Cognitive Experimental Paradigms

  Jiaqi Ding, Guorong Wu · 28. September 2026

  Agent memory systems are increasingly used to maintain long-term user preferences, task states and evolving facts, but current evaluations often collapse memory behavior into final-answer accuracy. We introduce MemProbe, a cognitive-science-inspired framework for diagnosing stability-plasticity trad…

• A Benchmarking Framework for Context-aware XR Interfaces

  Hyunsung Cho, Sarah Yewon Yun, Nancy Ruonan Sun, Ben Lafreniere, Mark Parent, Kashyap Todi, Tanya R. Jonker, Hrvoje Benko, Sherry Tongshuang Wu, David Lindlbauer · 28. September 2026

  Everyday Extended Reality (XR) systems aim to provide context-aware access to the right functionalities at the right time and place, with minimal manual reconfiguration as users switch context. Yet these interfaces are hard to evaluate: current prototyping and user-study workflows offer no systemati…