Episodic Memory

Follow this topic Ask about this topic

Episodic memory studies how systems retain and retrieve particular past events together with their temporal, spatial, and situational context, rather than only general facts. Common approaches use explicit episode stores, hierarchical or graph-based memories, compressed histories, and learned mechanisms for deciding what to store, forget, or retrieve. Systems are evaluated on multi-session question answering, streaming egocentric video, interactive tasks, and embodied settings where agents must reuse past experience. A central tension is how to compress and organize long histories without losing exact details or temporal grounding, especially when scenes change or new experiences interfere with earlier memories.

Latest papers

40 papers7 papers in the last four weeks, up 133% on the four weeks before. 0.0% of all new papers.

inr2action: Encoding Robot Episodes as Neural Implicit Representations for Recall and Action
Oct 20, 2026Leann Alhashishi, Christos Margadji, Sebastian William PattinsonLong-Term Memory for Embodied Agents Memory-Augmented Agents
Institute for Manufacturing, Department of Engineering, University of Cambridge · Matta Labs, 77 East Road, London, United Kingdom
EgoProbe: Benchmarking Long-Range and Exact Memory in Streaming Egocentric Videos
Oct 12, 2026Haokai Pang, Yuqian Fu, Yifei Wang +4Egocentric Video Understanding Streaming Video Understanding
HKUST · KAUST · ECNU +1
Event Memory and Narrative Dynamics: A Large Language Model Framework for Multidimensional State Spaces
Oct 12, 2026Joshua SariñanaEpisodic Memory Cognitive Modeling
Research Affiliate, Massachusetts Institute of Technology
A small cognitive core explains human behavior at scale
Oct 9, 2026Marcel Binz, Eric SchulzCognitive Modeling Human Behavior Modeling
Institute for Human-Centered AI, Helmholtz Munich, Neuherberg, Germany · Max Planck Institute for Biological Cybernetics, Tübingen, Germany
Never Look Back: Understanding Persistence in 3D Object Memory from Egocentric Videos
Oct 7, 2026Shravan Chaudhari, William Paul, Suchi Saria +2Memory-Augmented Video Understanding Egocentric Video Understanding
Johns Hopkins University · Johns Hopkins University Applied Physics Laboratory
A neural network that maintains and retrieves memories based on context
Sep 29, 2026Hayoung Song, JeongJun Park, Qihong Lu +4Episodic Memory Recurrent Neural Networks
Department of Psychology, University of Texas at Austin · Center for Theoretical and Computational Neuroscience, Washington University in St. Louis · Department of Neuroscience, University of Texas at Austin +6
Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models
Sep 28, 2026Beomsu Kim, Chieh-Hsin Lai, Bac Nguyen +3Multimodal Memory World Model Learning
KAIST · Sony Group Corporation · Imperial College London
MemTransfer: Benchmarking Memory Beyond Matched Experience in Embodied Decision-Making
Sep 26, 2026Haiming Tang, Xianjie Dai, Gujie Shao +5Memory Agent Benchmarks Episodic Memory
National University of Singapore · Korea Advanced Institute of Science and Technology · McGill University
MessyMem: Learning-from-Doing Memory for Mobile Manipulation
Sep 14, 2026Anuva Banwasi, William Muckelroy, Priya Sundaresan +3Long-Horizon Robotic Manipulation Mobile Manipulation
Stanford University
CreaMem: A Scene-Aware Memory Architecture for Personalized Agents
Sep 8, 2026Qixuan Sun, Yue Que, Bowei He +4LLM Agent Memory Episodic Memory
City University of Hong Kong, Hong Kong SAR, China · AgentWoods Inc., San Francisco · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE
Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context
Aug 26, 2026Zhexi Feng, Ruiyi Zhang, Yongbo Yang +1Conversational Memory Temporal Reasoning in Language Models
Department of Electrical and Computer Engineering University of California San Diego
Advantage-Driven Explicit Memory for Social Navigation
Aug 26, 2026Yeonsoo Park, Mattia Racca, Guillaume Bono +4Memory-Augmented Agents Robot Policy Generalization
Interdisciplinary Program in Artificial Intelligence, Seoul National University, Korea · Naver Labs Europe, France
Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B
Aug 24, 2026Defu Lin, Wenhui Chen, Ziyao Lin +3Efficient Multimodal Inference Multimodal Agents
University of Macau, Macao SAR, China · South China University of Technology, Guangzhou, China · independent researcher
ECHO: An Auditable Dual-Path Memory System for Long-Horizon Agents
Aug 22, 2026Yu Qian, Hong Miao, Boyang Guo +5Agent Memory Management Long-Term Memory for Embodied Agents
XDream Robotics, Building T2, Moli Community, No. 1, Lane 188, Yuren Road, Pudong New Area, Shanghai 200120, China
Remember Smarter: Visual History Compressor and Hyperbolic Experience Space for Robotic Memory
Aug 15, 2026Dai Zhou, Jiexi Yan, Tong Li +2Memory-Augmented VLMs Robot Policy Learning
Xidian University
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding
Aug 7, 2026Yeeun Choi, Youngbeom Yoo, Joon-Young Lee +2Memory-Augmented VLMs Episodic Memory
Yonsei University · Adobe Research
Caching for the Future: Scrub Jay Episodic Memory Principles for Agent Memory Systems
Aug 5, 2026Kartikey Singh Bhandari, Aarya Wadhwani, Dhruv Kumar +1Temporal IR Episodic Memory
Birla Institute of Technology and Science, Pilani
FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory
Aug 5, 2026Zhuoran Zhang, Bowen Li, Jingcheng Ju +5GUI Agents Episodic Memory
School of Computer Science, Peking University · 2Key Lab of High Confidence Software Technologies, Peking University · Institute of Information Engineering, Chinese Academy of Sciences +1
Not Forgotten: Implementation and Evaluation of a Personalized Episodic Memory for the Humanoid Robot Head Kim
Jul 27, 2026Steve Aschenbrenner, Marcel Heisler, Thomas Sievers +1Conversational Memory Episodic Memory
Stuttgart Media University, Germany · University of Lübeck
LightMem-Ego: Your AI Memory for Everyday Life
Jul 13, 2026Yijun Chen, Boyi Xiao, Yixian Zhao +10Multimodal Memory Episodic Memory
1Zhejiang University · 2South China University of Technology · 3Central China Normal University +1
Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing
Jul 9, 2026Feng Wang, Canmiao Fu, Zhipeng Huang +3Multimodal Memory Episodic Memory
Peking University · WeChat Vision, Tencent Inc.
S-EMBER: A Large-Scale Benchmark for Streaming Egocentric Memory Retrieval
Jul 2, 2026Xiaodong Wang, Xuanyi Zhao, Pedro Rodriguez +7Temporal Video Grounding Episodic Memory
1FAIR, Meta · 2Reality Labs, Meta
Surprise as a Signal for Plasticity and Metacognition
Jun 30, 2026Louis MouchonEpisodic Memory Metacognition in Language Models
Independent Research
Improving Human-Robot Teamwork in Urban Search and Rescue Through Episodic Memory of Prior Collaboration
Jun 17, 2026Taewoon Kim, Emma van Zoelen, Mark NeerincxEpisodic Memory Robotics
HumemAI, The Netherlands · Vrije Universiteit Amsterdam, The Netherlands · TNO, The Netherlands
Position: Hippocampal Explicit Memory Is the Cornerstone for AGI
Jun 5, 2026Sangjun ParkMemory-Augmented Language Models LLM Memory
Department of Computer Science, University of Texas at Austin, TX, USA · Cognizant AI Labs, San Francisco, CA, USA
Worth Remembering: Surprise-Gated Robot Episodic Memory
Jun 2, 2026Nicolas Gorlo, Derek K. Wise, Alberto Speranzon +1Embodied QA Episodic Memory
Massachusetts Institute of Technology · Lockheed Martin
EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision
May 29, 2026Rosario Forte, Giuseppe Lando, Antonino FurnariVLM Evaluation Streaming Video Understanding
Department of Mathematics and Computer Science University of Catania
Useful Memories Become Faulty When Continuously Updated by LLMs
May 13, 2026Dylan Zhang, Yanshan Lin, Zhengkun Wu +4AI Agent Reliability Persistent Memory for Language Models
University of Illinois Urbana-Champaign · IIIS, Tsinghua University
The Interference Gap: Comparing Retrieval Bounds in Human Memory and RAG Systems
May 9, 2026Dongxin Guo, Jikun Wu, Siu-Ming YiuComputational Cognitive Modeling Episodic Memory
The University of Hong Kong, Hong Kong, China · Stellaris AI Limited, Hong Kong, China · Brain Investing Limited, Hong Kong, China
ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting
May 5, 2026Jiale Chang, Yuxiang RenMultimodal Memory LLM Agent Memory
Nanjing Agricultural University · Nanjing University

Oct 20, 2026J/K move · Enter open · S save

inr2action: Encoding Robot Episodes as Neural Implicit Representations for Recall and Action

Leann Alhashishi, Christos Margadji, Sebastian William Pattinson

Institute for Manufacturing, Department of Engineering, University of Cambridge · Matta Labs, 77 East Road, London, United Kingdom

Long-Term Memory for Embodied Agents Memory-Augmented Agents Robot Learning Episodic Memory Implicit Neural Representations

Open paper AskPDF arXiv

Long-horizon robotic operation requires memory that scales with essential information rather than execution time. We present a parameter-space memory framework where each episode is stored as a separable object. A neural implicit representation is fitted to episode video from a shared, meta-learned initialization; the resulting weight delta constitutes the memory. Crucially, this delta remains a fixed size regardless of whether the episode spans a hundred or a hundred thousand frames. A learned projector maps the weight delta into token embeddings, conditioning a language model for question answering and a decoder for joint command regression, without frame retrieval at query time. On RoboMME, the language model exceeds chance across all question types, and the decoder achieves a mean

R^2

of 0.51. Replacing the delta with matched noise drops performance by 11.4 points, while random-origin weights are non-decodable, proving the meta-learned initialization is essential for embedding episode content. By representing individual experiences as fixed-size weight deltas in a common parameter space, this approach decouples memory cost from time horizon and provides a basis for scalable streaming memory.