---
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"}
---

# VeriHarness — Scaling Agentic Verification for Long-Horizon Tasks

## Retrieval answer

Google Cloud AI Research and the University of Cambridge present VeriHarness, a harness for verifying long-horizon agent outputs.

Google Cloud AI Research and the University of Cambridge present VeriHarness, a harness for verifying long-horizon agent outputs. The system generates multiple candidate rollouts with the same model, then conducts separate investigations into claims where rollouts disagree and claims on which they all agree. The investigations use environmental evidence and feed an adjudication step that delivers a revised artifact with a verification record.

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 results describe a specific evaluation using two frontier models; the page also notes added tool calls and latency. They do not establish that the harness improves every task or model.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Google](https://newruntime.com/topics/google.md): Explore the google topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)