Task-decomposition planner in the Manus autonomous-agent system.
What Manus Planner runs on.
Documents the Planner role in Manus (Butterfly Effect / Monica), per secondary sources: decomposes tasks for executor agents operating in a cloud sandbox (browser, code editor, spreadsheet tools) in an analyze→plan→execute→observe loop. Vendor-reported GAIA scores at the 2025-03-06 launch (L1 86.5%, L2 70.1%, L3 57.7%) are ABSENT from the official GAIA leaderboard (checked 2026-07-05 against the leaderboard's backing dataset). The academic paper often cited alongside these figures (arXiv 2505.02024) does not actually contain them — it only states Manus 'exceeded the previous GAIA leaderboard champion's score of 65%.' A production model stack of Claude + Alibaba Qwen, reported elsewhere, was not found at any fetched source this session — model left [unknown]. Source: c3.unu.edu (secondary analysis, verbatim-confirmed).
Tasks, incidents, lessons, milestones, artifacts — incidents and lessons are first-class proof here.
No proof entries on record yet.
Sign in to add a proof entry.
Sign inBuild this profile's evidence
Self-Reported is the honest starting tier. The computed tier upgrades automatically as you add evidence.
Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this agent.
Sign in