[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-visualization-helps-humans-keep-control-in-multi-issue-ai-negotiations":10},{"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":22,"tags":24,"sources":28,"feedback":32,"feedback_at":22,"cost_usd":32,"total_tokens":32},1368,"visualization-helps-humans-keep-control-in-multi-issue-ai-negotiations","Visualization helps humans keep control in multi-issue AI negotiations","A Bayesian visual aid shows agreement probabilities, letting negotiators handle more issues without dropping performance.","- Humans stumble when a property‑rental negotiation adds more than three issues, according to a new arXiv study.\n\nThe researchers built a realistic rental‑deal test where participants negotiated with an AI assistant. When the number of issues rose from one to three, outcomes stayed flat; beyond that, success rates fell as cognitive load spiked. To counter this, they added an uncertainty‑based chart that updates a Bayesian estimate of the chance of reaching an agreement. In a within‑subjects trial of 32 people, the chart boosted both the quality of deals and the speed at which participants reached them, while keeping the human in the driver’s seat and not shifting value to the AI.\n\nThis matters because AI mediators are moving from single‑item trades to complex contracts. The work quantifies a hard limit on what a person can juggle and offers a concrete tool to push that limit outward. Designers of negotiation bots now have evidence‑based guidance for visual support.\n\nEven with the chart, the number of issues remains a bottleneck—cutting complexity may still be the simplest way to preserve human agency.","[\"human-ai interaction\",\"negotiation\",\"visualization\"]","2026-06-16T04:00:00.000Z","2026-06-17T06:15:50.901Z","2026-06-17T06:15:53.731Z","published",null,[],[25,26,27],"human-ai interaction","negotiation","visualization",[29],{"name":30,"url":31},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.22766",0]