Continual Test-Time Adaptation

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 167% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 45

All topics

AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
May 29, 2026Zheyuan Zhang, Zehao Wen, Alvin Zhang +4Continual Test-Time Adaptation Long-Horizon Agent Evaluation
Johns Hopkins University
Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert Calibration
May 27, 2026Haonan Wen, Hanyang Chen, Songhe FengIrregular Time-Series Modeling Multivariate Time Series Forecasting
Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education School of Computer Science and Technology, Beijing Jiaotong University Beijing, China · School of Computer Science and Technology, Beijing Jiaotong University Beijing, China · Tangshan Research Institute, Beijing Jiaotong University Tangshan, China
Asymmetric Adaptation-based Real-time Fault Diagnosis Under Transitional Operating Conditions
May 23, 2026Hongshuo Zhao, Zeyi Liu, Xiao HeContinual Test-Time Adaptation Prototype Learning
MCC5 Group Shanghai Co. LTD Shanghai, China
Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation
May 22, 2026Zixuan Hu, Xuantuo Huang, Yancheng Li +3VLM Adaptation Continual Test-Time Adaptation
School of Computer Science, Peking University, Beijing, China · School of Electronics, Peking University, Beijing, China · Peng Cheng Laboratory, Shenzhen, China
GoTTA be Diverse: Rethinking Memory Policies for Test-Time Adaptation
May 19, 2026Shyma Alhuwaider, Yasmeen Alsaedy, Merey Ramazanova +2Test-Time Adaptation Continual Test-Time Adaptation
Center of Excellence in Generative AI, KAUST, Saudi Arabia
Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging
May 18, 2026Zhilin Zhu, Yabin Wang, Zhiheng Ma +3Distribution Shift Robustness Test-Time Adaptation
Harbin Institute of Technology · Pengcheng Laboratory · Shenzhen University of Advanced Technology +1
MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
May 18, 2026Ronyu Zhang, Aosong Cheng, Gaole Dai +8Activation Sparsity Mixture of Experts
Nanjing University · The Hong Kong Polytechnic University · State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University +3
FutureSim: Replaying World Events to Evaluate Adaptive Agents
May 14, 2026Shashwat Goel, Nikhil Chandak, Arvindh Arun +5Continual Test-Time Adaptation Forecasting Benchmarks
1ELLIS Institute Tübingen · 2Max Planck Institute for Intelligent Systems · 4Tübingen AI Center +3
Test-Time Learning with an Evolving Library
May 14, 2026Weijia Xu, Alessandro Sordoni, Chandan Singh +4Memory-Augmented Language Models Continual Test-Time Adaptation
Microsoft Research
Reliability-Gated Source Anchoring for Continual Test-Time Adaptation
May 13, 2026Vikash Singh, Debargha Ganguly, Weicong Chen +8Test-Time Adaptation Continual Test-Time Adaptation
1Case Western Reserve University · 2Université Laval · 3Mila - Québec AI Institute
Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
May 11, 2026Jianchao Zhao, Huoren Yang, Yusong Hu +6Continual Test-Time Adaptation Robotic Manipulation
College of Artificial Intelligence, Xi’an Jiaotong University · 2One Robotics · 3Shenzhen University of Advanced Technology
Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation
Apr 23, 2026Yingkai Yang, Chaoqi Chen, Hui HuangDomain Adaptation Continual Test-Time Adaptation
College of Computer Science and Software Engineering, Shenzhen University
Toward Robust Open-set Adaptation: Synapse Consolidation Inspired by Rac1/MAPK Pathways
Apr 1, 2026Xiao Zhang, Tianyu Hu, Juntao Lyu +2Test-Time Adaptation Unsupervised Domain Adaptation
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, 100083, China. · Department of Automation, Tsinghua University, Beijing, 100084, China.
Audio-Visual Continual Test-Time Adaptation without Forgetting
Feb 20, 2026Sarthak Kumar Maharana, Akshay Mehra, Bhavya Ramakrishna +2Cross-Modal Learning Source-Free Domain Adaptation
The University of Texas at Dallas · Dolby Laboratories
TestDG: Test-time Domain Generalization for Continual Test-time Adaptation
Date pendingSohyun Lee, Nayeong Kim, Juwon Kang +2Continual Test-Time Adaptation Cross-Domain Generalization
POSTECH · GenGenAI · KAIST AI

May 29, 2026, cs.CLJ/K move · Enter open · S save

AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents

Zheyuan Zhang, Zehao Wen, Alvin Zhang, Andrew Wang+3

Johns Hopkins University

Continual Test-Time Adaptation Long-Horizon Agent Evaluation AI Agent Benchmarks

Open paper AskPDF arXiv

For agents to learn continuously from interaction with the world at test time, they must be able to explore effectively, acquire new world knowledge and skills, retain relevant episodic experiences, and plan over long horizons. To evaluate these key abilities of test-time continual learning agents, we introduce AgentOdyssey, a novel evaluation framework that procedurally generates open-ended text games with rich entities, world dynamics, and long-horizon tasks. Critically, AgentOdyssey goes beyond the conventional machine learning assumption that learning does not occur at test time by placing agents in a continuous, long-horizon setting that interleaves learning and inference throughout deployment. We further propose a multifaceted evaluation methodology that measures not only game progress but also offers diagnostic tests on world knowledge acquisition, episodic memory, object and action exploration, action diversity, and model cost. We evaluate diverse agent paradigms in the generated games. Our experimental results reveal critical limits in agents' key abilities, as well as factors that influence their meaningful horizon. Although performance scales with stronger base models, even the top agent remains far below human performance, leaving substantial headroom for improvement. Among agent mechanisms, we find that short-term memory benefits multiple agent paradigms and is an important component of agent test-time training.

Momentum

Related topics

Latest papers 45