{
 "schema_version": 1,
 "generated": "2026-10-19",
 "id": "google-research-harness2--compare-parallel-vs-sequential-recursion",
 "repo": "google-research/harness2",
 "repo_url": "https://github.com/google-research/harness2",
 "repo_slug": "google-research-harness2",
 "title": "Compare parallel and sequential refinement on the same task",
 "page_title": "How to compare parallel and sequential refinement on the same task with harness2",
 "summary": "Run the same benchmark task in both recursion modes to pick the cheaper or stronger refinement strategy.",
 "who": "ML engineer deciding how to spend an agent-refinement compute budget on a recurring task type",
 "problem": "It is unclear whether exploring many candidates at once or refining step by step gives better results per dollar for your task.",
 "outcome": "Two reports for the same task, one per mode, that you can compare side by side to choose a strategy.",
 "steps": [
  "Run parallel mode: harness2 --bench lab --k 2 --mode parallel --only-domains antitrust-competition --max-tasks 1",
  "Run sequential mode: harness2 --bench lab --k 2 --mode sequential --only-domains antitrust-competition --max-tasks 1",
  "Judge each run: harness2-judge --bench lab --k 2 --mode parallel and harness2-judge --bench lab --k 2 --mode sequential",
  "Report each run: harness2-report --bench lab --k 2 --mode parallel and harness2-report --bench lab --k 2 --mode sequential",
  "Compare the two reports and the adopted harnesses."
 ],
 "agent_prompt": "Using google-research/harness2, run LAB on one task with --k 2 in both parallel and sequential modes, judge and report each, and tabulate the scores side by side. Verify both runs used the same task selection and seed before comparing.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "2 hours",
 "basis": "readme",
 "caveat": "A single task is a very noisy comparison, and the README ties each judge and report call to its own mode, k and seed, so run the full command set once per mode.",
 "category": "Research & Knowledge",
 "tags": [
  "Research & Knowledge"
 ],
 "lang": "python",
 "requirements": [
  "Linux, Python 3.12 and uv for installation",
  "No credentials needed for the local demo (harness2-demo)",
  "Model-backed runs need Node.js 20+, the Google Cloud CLI, a Vertex AI project and model IDs in .env, and gcloud application-default login",
  "LAB needs Pandoc and Poppler; WorkBuddy-Bench needs Docker",
  "Model-backed benchmark runs incur API costs"
 ],
 "risk": "dual-use",
 "seen_in_the_wild": false,
 "best": false,
 "score": 0.513,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/google-research-harness2/compare-parallel-vs-sequential-recursion/",
 "md": "https://dedupedai.com/use-cases/google-research-harness2/compare-parallel-vs-sequential-recursion/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly."
}