[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-profiler-turns-ai-agent-runs-into-flame-graphs":10,"sections":35},{"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":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},6811,"new-profiler-turns-ai-agent-runs-into-flame-graphs","New Profiler Turns AI Agent Runs Into Flame Graphs","AgentPProf borrows systems-style profiling to show which subtasks in long-running AI agents burn the most tokens and cause failures.","A new tool treats AI agent runs the way engineers treat slow code: something you can flame-graph.\n\nAgentPProf is a profiler built for AI agents that now run for days or weeks, juggling tools and system resources on a single task. Instead of tracking code paths like a traditional profiler, it models agent trajectories as a \"semantic operation stack,\" recursively splitting a run at task boundaries to attribute cost and failures to specific subtasks like diagnosing an error or comparing branches. It then aggregates those trajectories into pprof-compatible profiles, so developers get the same flame-graph visualizations systems programmers already use for CPU and memory bottlenecks. On CodeTraceBench, it hit a 0.764 B3 F1 score against human annotations, and on three problem-localization benchmarks its profiles improved MAP by up to 56 percent. The code is open-source on GitHub under eunomia-bpf\u002Fagentsight.\n\nThis matters because agent observability has mostly meant per-run debugging and tracing, useful for figuring out why one execution broke but useless for spotting patterns across hundreds of runs. Teams building long-horizon agents are essentially flying blind on which recurring subtasks quietly burn most of their token budget or trigger unsafe actions. A working cross-run profiler is the same shift performance engineering went through decades ago, moving from print-statement debugging to aggregate hotspot analysis.\n\nIt is worth remembering this is a preprint, not a production-hardened tool, and \"task intent\" is a far fuzzier unit to profile reliably than a function call. Whether AgentPProf holds up outside its own benchmarks is the real test.","[\"ai-agents\",\"profiling\",\"dev-tools\",\"open-source\"]","2026-09-18T04:00:00.000Z","2026-09-18T17:45:41.636Z","2026-09-18T17:45:52.616Z","published",null,[],"ai",[26,27,28,29],"ai-agents","profiling","dev-tools","open-source",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.20301",0,{"sections":36},[37,40,44,49,54,58,62,67,70,75,80,85,90,95],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",4017,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",653,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",338,"2026-09-11T04:00:00.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":18},"Hardware","hardware",155,{"name":59,"slug":60,"count":61,"latest_published_at":18},"Science","science",121,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",99,"2026-09-09T17:27:33.000Z",{"name":68,"slug":28,"count":69,"latest_published_at":18},"Dev Tools",77,{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",75,"2026-09-10T20:41:21.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Startups","startups",55,"2026-09-09T23:14:29.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",43,"2026-09-10T12:18:06.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"General","general",41,"2026-09-08T01:57:23.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]