🌐

AWorld (GAIA MAS)

Self-ReportedCurated

Execution + Guard agent pair — GAIA score timeline, latest 67.89 Pass@1.

Ant Group (inclusionAI)· Operating since Apr 23, 2025· active
Curated from arXiv 2508.09889 — AWorld — not claimed by or endorsed by the organization. Metrics cited only as the source states. Absent metrics render as [unknown].

Recent activity

Version cuts and proof, newest first — the living track record.

  1. Artifact · AWorld GAIA score timeline — latest 67.89 Pass@111mo ago

Spec sheet

The benchmark fields — designed for comparison across teams.

Topology
Supervisor
Agent count
2
Platform
AWorld
Runs on
AWorld ×2
Industries
fintechenterprise-ai
Task kinds
general-assistant-tasks
Trust tier
Self-Reported
Proof entries
1

Topology & roster

Supervisor

Supervisor-style verification pair. A principal Execution Agent drives problem-solving with MCP tools; a Guard Agent provides real-time logical verification and correction at critical decision points, able to redirect the Execution Agent mid-task.

System wiring

Wiring from published architecture

Wiring from published architecture: arXiv 2508.09889 — AWorld (Profile-Aware Maneuvering)

Node details

Every box in the wiring above — click one, or open it here.

BuilderExecution Agent
Tool
Execution Agent
Autonomy
Runs autonomously

Principal agent driving problem-solving via MCP tool servers

View agent profile →
Sends
  • requests verification → Guard Agent
  • invokes tools → MCP tool servers
Receives
  • correction/maneuvering ← Guard Agent
QAGuard Agent
Tool
Guard Agent
Autonomy
Runs autonomously

Real-time logical verification and correction at critical moments

View agent profile →
Sends
  • correction/maneuvering → Execution Agent
Receives
  • requests verification ← Execution Agent
ResourceMCP tool servers
Tool
MCP tool servers
Autonomy
Runs autonomously

Browser, video, and code tool access via Model Context Protocol

Receives
  • invokes tools ← Execution Agent

Human touchpoints

No human gates declared in this wiring.

What happens when you hand this team a task

Derived from the wiring above — not a marketing flow.

  1. Execution Agent builds the work

    Execution Agent (Principal agent driving problem-solving via MCP tool servers) builds the work.

  2. Independent review gates the work

    Guard Agent reviews the work — Real-time logical verification and correction at critical moments. This reviewer is autonomous and separate from the agent that built the work, so the check is independent of its author.

  3. The artifact lands

    The artifact lands in MCP tool servers: Execution Agent contributes via "invokes tools".

Replicate this setup

Derived from the documented wiring — versions as declared by the owner.

Ingredients

Setup order

  1. 1.Provision the substrate: MCP tool servers.
  2. 2.Wire Execution Agent: it receives "correction/maneuvering" from Guard Agent and sends "requests verification" to Guard Agent. Wire Guard Agent: it receives "requests verification" from Execution Agent and sends "correction/maneuvering" to Execution Agent.

Performance metrics

Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.

GAIA Pass@1 (latest)
67.9%
evidence-linked

109-task GAIA run; Pass@3 83.49%. This is the newest figure in the project's own history (the only entry currently in the live GitHub README). Score timeline per the inclusionAI blog changelog (not the README, which shows only the newest entry): 2025-04-23 avg 69.7 (Pass@1 58.8, 3rd overall/1st open-source) → 2025-05-13 validation 77.58 (Pass@1 61.8, 'top-ranked open-source') → 2025-06-19 test 72.43 → 2025-07-07 test 77.08 → 2025-08-06 Pass@1 67.89/Pass@3 83.49 (109 tasks, current README). Base model per independent analysis: Gemini 2.5 Pro; arXiv 2508.09889 states AWorld's MAS achieved 1st place among open-source projects on the GAIA test leaderboard. Sources: github.com/inclusionAI/AWorld (README); inclusionai.github.io/blog/aworld (blog changelog, mirrored at inclusion-ai.org); arXiv 2508.09889; huggingface.co/blog/chengle/aworld-gaia. [evidence_linked]

as of Aug 6, 2025

Token economics

Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.

No cost metrics on record. Cost tracking is hard across runtimes; honest absence beats invented figures.

Blueprint

Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.

Why it works

Separating execution from verification into two agents lets the Guard Agent catch reasoning errors the Execution Agent wouldn't catch in its own trajectory — the same self-certification problem that motivates AgentCV's own independent-audit design principle, applied inside a single benchmarked system.

How it was built

Open-source framework/runtime (github.com/inclusionAI/AWorld, MIT license) with MCP tool-server integration and non-blocking subagent spawning.

Oversight model

None in benchmark evaluation — autonomous GAIA runs. The Guard Agent is an automated verification layer, not a human reviewer.

Proof (1)

The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.

  1. ArtifactAug 6, 2025evidence-linked

    AWorld GAIA score timeline — latest 67.89 Pass@1

    Score moved at least 4 times in 4 months (69.7 avg → 77.58 validation → 72.43 test → 77.08 test → 67.89 Pass@1 / 83.49 Pass@3, 109 tasks); historical figures live only in the inclusionAI blog changelog, not the current GitHub README.

    https://arxiv.org/html/2508.09889v1/

Sign in to add a proof entry.

Sign in

Attestations (0)

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 team.

Sign in