Proactive Assistance

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 75% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 36

All topics

Improving Proactive AI Assistance with Hierarchical Procedural Understanding
Oct 5, 2026Jin-Seop Lee, TaeYeon Won, SeongJun Jung +5Vision-Language Models Proactive Assistance
Department of Artificial Intelligence, Sungkyunkwan University, Republic of Korea · College of Computing and Data Science, Nanyang Technological University, Singapore
Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym
Sep 29, 2026Jio Oh, Seunghyun Do, Young-Jun Lee +2LLM Agent Evaluation Long-Horizon Agent Evaluation
KAIST · University of Minnesota
Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
Sep 29, 2026Ido Levy, Asaf Yehudai, Segev Shlomov +2Proactive Assistance Tool-Using Agents
IBM · Weizmann Institute of Science
Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents
Sep 27, 2026Fuyao Zhang, Xuan Wang, Zherui Li +3Agent Memory GUI Agents
NTU & Alibaba
Robots That Take Initiative: A Framework for Building and Evaluating Proactive Robots
Sep 24, 2026Maithili Patel, Sonia ChernovaHuman-in-the-Loop Evaluation Robotic Policy Evaluation
School of Interactive Computing, Georgia Institute of Technology, USA
Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams
Sep 23, 2026Shujian Gao, Jiamei Yan, Yuchen Yang +6Human-AI Interaction Proactive Assistance
Institute of Trustworthy Embodied AI, Fudan University · ByteDance TikTok · Shanghai Innovation Institution +1
When2Talk: When Should a Proactive In-Car Agent Talk?
Sep 14, 2026Kaiser Hamid, Peihang Li, Nade LiangAutonomous Driving Proactive Assistance
Texas Tech University Lubbock, Texas, USA
When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI Systems
Sep 7, 2026João Dias FerreiraAgent Evaluation Proactive Assistance
Wyrde AI
Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation
Sep 3, 2026Yan Tang, Tingyu Cao, Yuanbo Tang +2LLM Agent Evaluation Proactive Assistance
UniCone Team
Designing Proactive Thought Partners for Writing
Sep 1, 2026Chao Zhang, Abe Davis, Chih-Wei Chen +1Proactive Assistance Human-AI Co-Creation
*Work done during an internship at Google DeepMind. · 1Cornell University · 2Google DeepMind
Towards Cognitive Process-Aware Proactive Writing Support
Aug 31, 2026Masahiro Yoshida, Atsuya Kobayashi, Kei Tateno +1Proactive Assistance
Sony Group Corporation Tokyo, Japan · University of California, Los Angeles Los Angeles, California, USA
VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?
Aug 11, 2026Xiaohongshu IncLong-Horizon Agent Evaluation AI Agent Benchmarks
Xiaohongshu Dots Studio · Evolvent AI
ProEvent: An Event-centric Benchmark for Proactive Agents
Jul 20, 2026Guanzhen Li, Liangming Pan, Leye WangLLM Agent Evaluation Proactive Assistance
School of Computing, Peking University
Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
Jul 13, 2026Gong Sitong, Tianyu Yan, Caixin Kang +6Egocentric Video Understanding Proactive Assistance
Dalian University of Technology · Alaya Lab · The University of Tokyo
Context Graphs for Proactive Enterprise Agents
Jul 4, 2026Avinash KumarProactive Assistance LLM Agents
ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration
Jul 4, 2026Shu Yang, Difei Xu, Jiaxin Pei +1LLM Agent Evaluation Proactive Assistance
1PRADA Lab, King Abdullah University of Science and Technology · 2Stanford University
When May I Help You? On The Effect of Proactivity on Group Human-Robot Collaboration
Jun 26, 2026Thomas Vitry, Vanessa Maeder, Kieran von Valeburg +6Proactive Assistance Human-Robot Collaboration
Knowledge Technology, University of Hamburg, Hamburg, Germany · Ecole Normale Superieure de Rennes, Rennes, France
Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance
Jun 3, 2026Kaustav Kundu, Ritvik Shrivastava, Maxim Arap +13LLM Planning Egocentric Video Understanding
1Meta Reality Labs · 2Meta Superintelligence Labs
Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents
Jun 2, 2026Zhijie Ding, Weinan Hong, Zicheng Zhu +6Efficient Multimodal Inference Proactive Assistance
HyperAI Team, Xiaomi Corporation · Zhongnan University of Economics and Law · 1HyperAI Team, Xiaomi Corporation +5
Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents
May 27, 2026Bin Wu, Guanyun Zou, Bingbing Wang +2LLM Agent Memory LLM Agent Evaluation
Beijing University of Posts and Telecommunications · Nanjing University of Aeronautics and Astronautics · Harbin Institute of Technology (Shenzhen) +1
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World
May 25, 2026Yusong Lin, Xinyuan Liang, Haiyang Wang +8Computer-Use Agent Benchmarks AI Agent Benchmarks
Beijing Institute of Technology · Huawei Technologies Co., Ltd · Peking University +1
ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents
May 24, 2026Lei Ding, Bin He, Chenguang Wang +1Proactive Assistance Conversational Agents
University of California, Santa Cruz · 2Zillow Group
TRAFA: Anticipating User Actions to Reduce Errors in Procedural Tasks with Predictive Feedback
May 23, 2026Sassan Mokhtar, Lars Doorenbos, Fatemeh Jabbari +3Proactive Assistance Human Behavior Prediction
University of Bonn · Bonn, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence
PACT: Proactive Asking for Continual Task Assistance in Human-Robot Collaboration
May 23, 2026Chengbo He, Sheng Li, Chenyang Ma +6Proactive Assistance Human-Robot Collaboration
University of Science and Technology Beijing · University of Oxford · 3Tsinghua University
$π$ -Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
May 14, 2026Haoran Zhang, Luxin Xu, Zhilin Wang +11Long-Horizon Agent Evaluation AI Agent Benchmarks
Shanghai Jiao Tong University · Shanghai AI Laboratory · Fudan University +7
Exploring Human-Robot Collaboration: Analysis of Interaction Modalities in Challenging Tasks
May 13, 2026Simone Arreghini, Cristina Iani, Alessandro Giusti +3Proactive Assistance Human-Robot Collaboration
Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland · Department of Surgery, Medicine, Dentistry and Morphological Sciences with interest in Transplant, Oncology and Regenerative Medicine, University of Modena and Reggio Emilia, Modena, Italy. · Department of Sciences and Methods for Engineering (DISMI), University of Modena and Reggio Emilia, Reggio Emilia, Italy.
ProactBench: Beyond What The User Asked For
May 9, 2026Sepehr Harfi, Ahmad Salimi, Dongming Shen +1LLM Agent Evaluation Proactive Assistance
Boson AI Toronto, ON, Canada · Boson AI Santa Clara, CA, USA
An Empirical Study of Proactive Coding Assistants in Real-World Software Development
May 7, 2026Lehui Li, Ruixuan Jia, Guo-Ye Yang +1Sim-to-Real Transfer Intent Classification
College of AI, Tsinghua University, China · Fitten Tech Co., Ltd., China
Agentic Coding Needs Proactivity, Not Just Autonomy
May 7, 2026Nghi D. Q. Bui, Georgios EvangelopoulosAI Coding Agents Coding Agents
Google Labs
Pro $^2$ Assist: Continuous Step-Aware Proactive Assistance with Multimodal Egocentric Perception for Long-Horizon Procedural Tasks
May 5, 2026Lilin Xu, Bufang Yang, Siyang Jiang +6Proactive Assistance Multimodal Agents
Columbia University, United States · The Chinese University of Hong Kong, China

Oct 5, 2026, cs.LGJ/K move · Enter open · S save

Improving Proactive AI Assistance with Hierarchical Procedural Understanding

Jin-Seop Lee, TaeYeon Won, SeongJun Jung, JungHoon Kim+4

Department of Artificial Intelligence, Sungkyunkwan University, Republic of Korea · College of Computing and Data Science, Nanyang Technological University, Singapore

Vision-Language Models Proactive Assistance

Open paper AskPDF arXiv

Proactive AI assistants continuously observe a user's activity and decide whether to provide new guidance or remain silent. They should provide appropriate guidance for the task, determine when to provide the next guidance based on task progress, and adjust the guidance level to the user's expertise and needs. Supporting these capabilities requires training and evaluation data that reflect procedural structure and capture how guidance should adapt to task progress and user needs. However, existing datasets either focus on detection-based proactive understanding or provide procedural guidance at a fixed granularity. Fixed-granularity guidance provides limited information about fine-grained progress and broader procedural context, making it difficult to determine completion and adapt guidance granularity. To address these limitations, we introduce the ProactiveCoach suite, comprising ProactiveCoach-Instruct for training, ProactiveCoachBench for evaluation, and fine-tuned VLMs with an adaptive guidance system. ProactiveCoach-Instruct provides hierarchically structured guidance at the phase, step, and action levels for learning task progress and procedural context. ProactiveCoachBench evaluates whether models provide appropriate guidance at the right time across different guidance levels and adapt when the requested level changes. We fine-tune pretrained VLMs on ProactiveCoach-Instruct and demonstrate its effectiveness across backbones. Compared with fixed-granularity supervision, hierarchical supervision improves overall performance across backbones by up to 9.6%p. We further build an adaptive guidance system by combining our fine-tuned model with a lightweight guidance router. Without additional fine-tuning, our system outperforms the in-context adaptation baseline by 57.1%p across four guidance-level transitions. Our project page is available at https://jinsuby.github.io/ProactiveCoach/.

Momentum

Related topics

Latest papers 36