Skip to main content

# Embodied Memory

2 related articles

Subscribe to updates

arXiv Oct 8, 2026
EmbodiedRSI uses a hypothesis graph and value-of-information experiment selection to lift a frozen VLA to 77.0% on RoboCasa365 and 86.8% on LIBERO-Pro, transferring zero-shot to a real robot at 71.3%
EmbodiedRSI is a self-evolving agentic harness that, around a frozen robot foundation model, maintains code and skill hypotheses in a Hypothesis Graph, uses Value-of-Information Experiment Selection to pick the physical experiments that best distinguish them, and turns each interaction into reusable improvement through Code-Skill Co-Evolution and Reward-Grounded Memory Learning; it reaches 77.0% overall success on RoboCasa365 and 71.3% on Composite-Unseen (best baseline 40.1%), 86.8% overall on LIBERO-Pro, and transfers the simulation-evolved harness zero-shot to a real robot at 71.3% overall success.
EmbodiedRSI is a self-evolving agentic harness that, around a frozen robot foundation model, maintains code and skill hypotheses in a Hypothesis Graph, uses Value-of-Information Experiment Selection to pick the physical experiments that best distinguish them, and turns each interaction into reusable improvement through Code-Skill Co-Evolution and Reward-Grounded Memory Learning; it reaches 77.0% overall success on RoboCasa365 and 71.3% on Composite-Unseen (best baseline 40.1%), 86.8% overall on LIBERO-Pro, and transfers the simulation-evolved harness zero-shot to a real robot at 71.3% overall success.
Columbia University Princeton University
Python Song（First author）
EmbodiedRSI Harness Evolution Self-Evolving Agents Embodied Memory Sim-to-Real Transfer
arXiv Sep 29, 2026
ZJU team releases EMem-Bench: across 2,554 long-horizon embodied episodes the strongest model Gemini-3-Flash reaches only 64.2% average success, while its EMem memory system lifts GPT-5.4-mini by 23.6 points
The OmniAI Group of ZJU ACES Lab introduces EMem-Bench, a long-horizon embodied memory benchmark of 2,554 executable episodes spanning Passive Observation, Dynamic Tracking, Interaction Failure, and Experience Generalization, together with an external memory system EMem and an 8B policy EMem-8B; evaluating 16 open-source and proprietary MLLMs plus representative multimodal memory systems shows the strongest proprietary model Gemini-3-Flash reaches only 64.2% average success rate and most open-source models fall below 45%, while EMem achieves the best overall performance among matched backbones, improving Mistral-Small-3.1-24B by 16.4 points and GPT-5.4-mini by 23.6 points, with EMem-8B improving over Qwen3-VL-8B by 20.6 points.
The OmniAI Group of ZJU ACES Lab introduces EMem-Bench, a long-horizon embodied memory benchmark of 2,554 executable episodes spanning Passive Observation, Dynamic Tracking, Interaction Failure, and Experience Generalization, together with an external memory system EMem and an 8B policy EMem-8B; evaluating 16 open-source and proprietary MLLMs plus representative multimodal memory systems shows the strongest proprietary model Gemini-3-Flash reaches only 64.2% average success rate and most open-source models fall below 45%, while EMem achieves the best overall performance among matched backbones, improving Mistral-Small-3.1-24B by 16.4 points and GPT-5.4-mini by 23.6 points, with EMem-8B improving over Qwen3-VL-8B by 20.6 points.
Zhejiang University Central South University Chinese Academy of Sciences
Lizhou Liang（First author）
EMem-Bench Embodied-Memorizer Embodied Memory Agent Memory

You’re all caught up