[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-sensewalk-uses-llms-to-simulate-why-people-move":10,"sections":34},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},3281,"sensewalk-uses-llms-to-simulate-why-people-move","SenseWalk Uses LLMs to Simulate Why People Move","A new research system pairs large language models with a physics model to generate realistic crowd movement data without the cost of collecting it in the field.","Researchers have built a tool that simulates how people move through spaces — and why — using AI agents instead of expensive real-world data collection.\n\nThe system, called SenseWalk, combines large language models with something called the social force model, a physics-based approach to crowd behavior. The idea is that LLMs can reason about visitor profiles and goals — the semantic layer of movement — while the physics model keeps the simulated paths from looking physically absurd. The result is synthetic trajectory data that carries meaning beyond raw coordinates. A user study with 12 participants tested the interface, which is designed to let non-experts configure simulations and read the outputs without needing a background in modeling.\n\nThe practical problem SenseWalk is trying to solve is real: collecting high-quality movement data in venues like museums, hospitals, or transit hubs is slow, expensive, and rarely comes with the behavioral context that makes it useful for analysis. If synthetic data can stand in, researchers and planners get a cheaper path to understanding crowd behavior — and can run scenarios that would be impossible or unethical to stage in the real world.\n\nIt is worth noting this is a preprint, not a peer-reviewed result, and a user study of 12 people is thin ground for broad claims about usability. The harder test will be whether SenseWalk's synthetic trajectories hold up against real data in production settings.","[\"ai\",\"simulation\",\"research\",\"urban-mobility\"]","2026-07-02T04:00:00.000Z","2026-07-02T06:33:34.867Z","2026-07-02T06:33:37.824Z","published",null,[],"ai",[24,26,27,28],"simulation","research","urban-mobility",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.00989",0,{"sections":35},[36,40,45,50,55,60,65,70,75,80,85,89,94,99],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":86,"slug":87,"count":83,"latest_published_at":88},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]