{"type":"raw_signal","id":"veriharness-scaling-agentic-verification-for-long-horizon-tasks-535ee6","slug":"veriharness-scaling-agentic-verification-for-long-horizon-tasks-535ee6","title":"VeriHarness — Scaling Agentic Verification for Long-Horizon Tasks","description":"Google Cloud AI Research and the University of Cambridge present VeriHarness, a harness for verifying long-horizon agent outputs.","retrieval_nugget":"Google Cloud AI Research and the University of Cambridge present VeriHarness, a harness for verifying long-horizon agent outputs.","observed_at":"2026-10-07","record_date":"2026-10-07","date_kind":"observed_at","why_it_matters":"The project page reports evaluation across five benchmarks covering documents, spreadsheets, code, and multi-file workspace tasks. With ten rollouts per task, the reported average native benchmark score for Gemini 3.5 Flash rises from 47.2 for a single rollout to 53.4 after evidence-backed revision. The authors report the highest primary selection score in all ten model–benchmark settings. The res","novelty":"notable","verification_level":"source-linked","signal_type":"research","source_platform":"veriharness.com","topics":["google"],"entities":[],"related_patterns":[],"source_url":"https://veriharness.com/","source_urls":["https://veriharness.com/"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"signal:veriharness-scaling-agentic-verification-for-long-horizon-tasks-535ee6","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/signals/veriharness-scaling-agentic-verification-for-long-horizon-tasks-535ee6/","markdown":"https://newruntime.com/signals/veriharness-scaling-agentic-verification-for-long-horizon-tasks-535ee6.md","json":"https://newruntime.com/signals/veriharness-scaling-agentic-verification-for-long-horizon-tasks-535ee6.json"},"next_reads":[{"type":"topic","path":"/topics/google/","url":"https://newruntime.com/topics/google/","title":"Google","reason":"Explore the google topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/google.md","json_url":"https://newruntime.com/topics/google.json"},{"type":"collection","path":"/signals/","url":"https://newruntime.com/signals/","title":"Raw Signals","reason":"Open every source-linked raw signal.","media_type":"text/html","json_url":"https://newruntime.com/signals.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}