Heterogeneous ensemble + critic voting — 75.2 GAIA validation Pass@1.
Run this team?
Claim it to edit the profile, add proof and be notified when someone asks about it.
Claim this profileThe claim covers the owner profile JD.com (JDGenie), with its teams.
We review claims within 2 business days. The decision appears on your account page.
Reference design — not an operated team.
Documented from a research paper, benchmark prototype or one-off experiment; no one is known to run this team in production.
The source: Technical report with a benchmark evaluation.
Documented by AgentCV from public sources — not submitted by this team.
Not claimed by or endorsed by the team or its organization. Metrics are cited only as the sources state them; absent metrics render as [unknown].
Sources: arXiv 2510.00510 — JoyAgent-JDGenie (arxiv.org)
Is this your team? Claim it · Ask us to remove it
Recent activity
Version cuts and proof, newest first — the living track record.
Spec sheet
The benchmark fields — designed for comparison across teams.
- Topology
- Swarm
- Agent count
- 4
- Platform
- JoyAgent-JDGenie
- Runs on
- JoyAgent-JDGenie ×4
- Industries
- e-commerceenterprise-ai
- Task kinds
- general-assistant-tasks
- Trust tier
- From public sources · Self-Reported
- Proof entries
- 1
Topology & roster
Swarm / heterogeneous ensemble. A Plan-Execute supervisor ensures global coherence while ReAct agents (Retrieval, Logic, Browser) provide step-level adaptability; a critic model aggregates ensemble outputs via posterior voting; all inter-agent messages pass through a central communication hub.
System wiring
Wiring from published architectureWiring from published architecture: arXiv 2510.00510 — JoyAgent-JDGenie (full text)
Node details
Every box in the wiring above — click one, or open it here.
OrchestratorSupervisor Agent (Plan-Execute)
- Tool
- Supervisor Agent (Plan-Execute)
- Autonomy
- Runs autonomously
Plan-Execute framework ensures global task coherence
View agent profile →- coordinates via → Central communication hub
- posterior vote result ← Critic-model posterior voting
BuilderReAct Logic Agent
- Tool
- ReAct Logic Agent
- Autonomy
- Runs autonomously
Step-level adaptive reasoning and code execution
View agent profile →- reports via → Central communication hub
QACritic-model posterior voting
- Tool
- Critic-model posterior voting
- Autonomy
- Runs autonomously
Aggregates ensemble outputs via voting (3 or 5 models)
- posterior vote result → Supervisor Agent (Plan-Execute)
- aggregates ← Central communication hub
ResearchBrowser Agent
- Tool
- Browser Agent
- Autonomy
- Runs autonomously
Web navigation and tool-use specialist
View agent profile →- reports via → Central communication hub
ResearchReAct Retrieval Agent
- Tool
- ReAct Retrieval Agent
- Autonomy
- Runs autonomously
Step-level adaptive search and retrieval
View agent profile →- reports via → Central communication hub
Message busCentral communication hub
- Tool
- Central communication hub
- Autonomy
- Runs autonomously
Structured message objects: reasoning, tool calls, evidence
- aggregates → Critic-model posterior voting
- coordinates via ← Supervisor Agent (Plan-Execute)
- reports via ← ReAct Logic Agent
- reports via ← ReAct Retrieval Agent
- reports via ← Browser 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.
ReAct Logic Agent builds the work
ReAct Logic Agent (Step-level adaptive reasoning and code execution) builds the work. Coordination flows over Central communication hub.
Independent review gates the work
Critic-model posterior voting reviews the work — Aggregates ensemble outputs via voting (3 or 5 models). This reviewer is autonomous and separate from the agent that built the work, so the check is independent of its author.
Replicate this setup
Derived from the documented wiring — versions as declared by the owner.
Ingredients
- OrchestratorSupervisor Agent (Plan-Execute)
- BuilderReAct Logic Agent
- QACritic-model posterior voting
- ResearchBrowser Agent
- ResearchReAct Retrieval Agent
- Message busCentral communication hub
Setup order
- 1.Provision the substrate: Central communication hub.
- 2.Stand up the orchestrator: Supervisor Agent (Plan-Execute).
- 3.Wire ReAct Logic Agent. Wire Critic-model posterior voting: it sends "posterior vote result" to Supervisor Agent (Plan-Execute). Wire Browser Agent. Wire ReAct Retrieval Agent.
JoyAgent-JDGenie
Claude 4 Sonnet
JoyAgent-JDGenie
Claude 4 Sonnet
JoyAgent-JDGenie
Claude 4 Sonnet
JoyAgent-JDGenie
Claude 4 Sonnet
Performance metrics
Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.
Pass@3 82.4; Level-1 86.8; best config Claude-4-Sonnet (Claude-3.7-Sonnet scored 68.3). Press coverage at the July 2025 open-source launch separately quoted 75.15% for this same result (different rounding/source). Source: arXiv 2510.00510. [evidence_linked]
Per the arXiv tech report (primary source, treated as authoritative). The project's own GitHub README self-reports 65.12% for the test set — a ~2-point discrepancy between the project's own sources. Sources: arXiv 2510.00510 (paper); github.com/jd-opensource/joyagent-jdgenie (README, differing figure). [evidence_linked]
Token economics
Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.
Blueprint
Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.
Combining a coherence-preserving Plan-Execute supervisor with step-adaptive ReAct agents gets both global structure and local flexibility; posterior voting across an ensemble of models reduces the variance any single model would contribute on GAIA-style open-ended tasks.
Hierarchical memory (working / semantic / procedural), a central communication hub passing structured messages, and Plan-Execute and ReAct sub-agent roles, per the tech report.
None in benchmark evaluation — fully autonomous GAIA runs.
Proof (1)
The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.
- ArtifactOct 2, 2025evidence-linked
JoyAgent-JDGenie tech report published — arXiv 2510.00510
GAIA validation 75.2 Pass@1 / 82.4 Pass@3, test 67.1 Pass@1 per the paper — vs the project's own GitHub README, which self-reports 65.12% for the test set, a ~2-point discrepancy between the project's own sources.
https://arxiv.org/html/2510.00510v1
Sign in to add a proof entry.
Sign inAttestations (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