[
    {
        "id": "osp-20744",
        "type": "article-journal",
        "title": "Simple Agentic Memory for Generalist Robot Policies",
        "author": [
            {
                "family": "Zhang",
                "given": "Yuyou"
            },
            {
                "family": "Zhang",
                "given": "Yunbei"
            },
            {
                "family": "Li",
                "given": "Miao"
            },
            {
                "family": "Wang",
                "given": "Janet"
            },
            {
                "family": "Jin",
                "given": "Zijian"
            },
            {
                "family": "Liu",
                "given": "Shilong"
            },
            {
                "family": "Zhao",
                "given": "Ding"
            }
        ],
        "URL": "https://omanscience.com/en/articles/simple-agentic-memory-for-generalist-robot-policies",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Visual-memory systems commonly retain or compress past observations. Robot control additionally requires interaction-derived state that no individual frame may explicitly represent, such as persistent identity relations, accumulated progress, or ordered procedures. We introduce Simple Agentic Robot Memory (SimpleARM), a training-free memory layer for frozen generalist robot policies. From the task instruction, SimpleARM specifies what to monitor; frozen perceptual tools maintain compact typed state online; structured access retrieves that state only when a proposed subgoal depends on history; and current-view grounding resolves recalled entities before execution. We evaluate SimpleARM on RoboMME, a benchmark of memory-dependent robot manipulation tasks that require history information no longer available in the current observation. Across all 16 tasks and three policy seeds, SimpleARM achieves 67.17% mean success, compared with 44.51% for the strongest non-oracle baseline. Matched ablations show mechanism specificity: removing relation, reference, progress, or route state produces large losses where the affected state is retrieved for control, while largely sparing other tasks. These results support a state-based view of robot memory: effective memory for control is not simply retained visual history, but compact task-relevant state derived from the interaction history."
    }
]