Agent teams for general assistant tasks

AWorld (GAIA MAS)

Ant Group (inclusionAI)

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

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

updated 1y ago

Supervisor2 agentsAWorld

Execution Agent· Gemini 2.5 ProGuard Agent· Gemini 2.5 Pro

fintechenterprise-ai

Outcome[unknown]

Economics[unknown] · deliberate

1 proof

🧩

Genspark Super Agent

MainFunc (Genspark)

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Mixture-of-agents across 9 LLMs — vendor-claimed 87.8% on GAIA.

updated 1y ago

Swarm1 agentGenspark

Mixture-of-Agents Orchestrator

consumer-ai

Outcome[unknown]

Economics[unknown] · deliberate

1 proof

🧠

h2oGPTe Agent

H2O.ai

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Enterprise agent + majority voting — claimed #1 on GAIA, Dec 2024.

updated 1y ago

Solo + Tools1 agenth2oGPTe

Solo Agent· Claude 3.5 Sonnet

enterprise-ai

Outcome[unknown]

Economics[unknown] · deliberate

1 proof

🧩

JoyAgent-JDGenie

JD.com (JDGenie)

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Heterogeneous ensemble + critic voting — 75.2 GAIA validation Pass@1.

updated 1y ago

Swarm4 agentsJoyAgent-JDGenie

Supervisor (Plan-Execute)· Claude 4 SonnetReAct Retrieval Agent· Claude 4 SonnetReAct Logic Agent· Claude 4 SonnetBrowser Agent· Claude 4 Sonnet

e-commerceenterprise-ai

Outcome[unknown]

Economics[unknown] · deliberate

1 proof

🪞

Leni

Dupple

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Planner + executor pool + per-step verification — vendor-claimed 77.6% on GAIA.

updated 6mo ago

Pipeline3 listed membersLeni (Dupple)

PlannerExecutor PoolPer-Step Verifier

real-estateinvestment

Outcome[unknown]

Economics[unknown] · deliberate

1 proof

🕶️

Manus

Butterfly Effect / Monica (Manus)

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Planner + executor in a cloud sandbox — vendor-claimed GAIA SOTA at launch.

updated 1y ago

Orchestrator–Worker2 listed membersManus

PlannerExecutor

consumer-ai

Outcome[unknown]

Economics[unknown] · deliberate

1 proof

Teams for general assistant tasks

AWorld (GAIA MAS)

Genspark Super Agent

h2oGPTe Agent

JoyAgent-JDGenie

Leni

Manus