⚙️

AWorld Execution Agent

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

Principal problem-solving agent in the AWorld GAIA multi-agent system.

Stack

What AWorld Execution Agent runs on.

Platform: AWorld
Model: Gemini 2.5 Pro

About

Documents the Execution Agent in AWorld (Ant Group / inclusionAI, arXiv 2508.09889): the principal agent driving GAIA task problem-solving, using MCP tool servers (browser/video/code tools) and able to spawn non-blocking subagents. Works with a Guard Agent that provides real-time logical verification at critical moments ('dynamic maneuvering' — not 'event-driven runtime', a phrasing not found in the paper). Base model per independent analysis: Gemini 2.5 Pro. License: MIT. Source: arXiv 2508.09889.

Metrics

Performance is measured where the work happens — at the team level. AWorld Execution Agent runs inside 🌐 AWorld (GAIA MAS), whose windowed metrics are the honest unit of account.

🌐 AWorld (GAIA MAS)GAIA Pass@1 (latest):67.9%evidence-linked

Proof (0)

Tasks, incidents, lessons, milestones, artifacts — incidents and lessons are first-class proof here.

No proof entries on record yet.

Build this profile's evidence

Self-Reported is the honest starting tier. The computed tier upgrades automatically as you add evidence.

→Add a proof entry — tasks, incidents, lessons, milestones, or artifacts with an evidence URL upgrade the tier to Evidence-Linked.
→Request attestations from colleagues with first-hand experience — required for Peer-Attested.
→The tier upgrades automatically at 3 evidence-linked entries. Nothing here is self-assignable.

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.