Multi-objective Bayesian search for team config — >45% cost reduction vs random.
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 2511.11788 — MALBO (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
- Supervisor
- Agent count
- 5
- Platform
- MALBO
- Runs on
- MALBO
- Industries
- researchsoftware-delivery
- Task kinds
- configuration-optimizationcost-performance-tradeoffteam-design
- Trust tier
- Self-Reported
- Proof entries
- 1
Topology & roster
Supervisor-style team design by search. MALBO searches the team-design space: which agent roles, which model per role, which team size. The output is an optimized team for a specific task type. The resulting team can be any topology (supervisor is the primary studied case).
System wiring
Node details
Typical Supervisor layout — schematic, not verified wiring
HumanHuman operatorHuman gate
- Tool
- Human operator
- Autonomy
- Human-gated
- directs → Supervisor
OrchestratorSupervisor
- Tool
- Supervisor
- Autonomy
- Runs autonomously
- dispatches → Worker agent A
- dispatches → Worker agent B
- directs ← Human operator
- reports ← Worker agent A
- reports ← Worker agent B
BuilderWorker agent A
- Tool
- Worker agent A
- Autonomy
- Runs autonomously
- reports → Supervisor
- dispatches ← Supervisor
BuilderWorker agent B
- Tool
- Worker agent B
- Autonomy
- Runs autonomously
- reports → Supervisor
- dispatches ← Supervisor
How a typical Supervisor team handles a task
Typical Supervisor layout — schematic, not verified wiring
Task arrives
Human operator directs Supervisor.
The orchestrator routes the work
Supervisor dispatches build work to Worker agent A and dispatches build work to Worker agent B.
The builders execute
Worker agent A and Worker agent B build the work.
Human holds the last word
Human operator holds final approval.
Replicate a typical Supervisor setup
Typical Supervisor layout — schematic, not verified wiring
Ingredients
- HumanHuman operator
- OrchestratorSupervisor
- BuilderWorker agent A
- BuilderWorker agent B
Setup order
- 1.Stand up the orchestrator: Supervisor.
- 2.Wire Worker agent A: it receives "dispatches" from Supervisor and sends "reports" to Supervisor. Wire Worker agent B: it receives "dispatches" from Supervisor and sends "reports" to Supervisor.
- 3.Declare the human gate: Human operator holds final approval.
Performance metrics
Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.
>45% cost reduction on average vs random search with comparable performance. Source: arXiv 2511.11788 [evidence_linked]
Up to 65.8% (best case): heterogeneous MALBO team vs a homogeneous baseline; comparable task performance. Source: arXiv 2511.11788 [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.
Bayesian optimization is sample-efficient — it finds good configurations in far fewer trials than random search. Multi-objective formulation explicitly trades off performance vs cost, producing configurations that are not needlessly expensive. Heterogeneous model assignment (different models per role) captures the insight that different tasks within a workflow have different capability requirements.
Python implementation using Bayesian optimization libraries. Task evaluated on a standardized benchmark. Team-design search space: model selection per role, number of agents, role assignments. Pareto-frontier search identifies team designs that are not dominated on both objectives simultaneously.
Multi-objective optimization loop is automated: it searches a Pareto front of accuracy vs cost with independent Gaussian-process surrogate models, with no human-set objective weights. A human picks the task and the search space. BO requires significantly fewer evaluations than random search (sample-efficient). Source: arXiv paper.
Proof (1)
The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.
- ArtifactNov 14, 2025evidence-linked
MALBO paper published — arXiv 2511.11788
>45% cost reduction vs random search; heterogeneous teams: up to 65.8% cost reduction vs homogeneous baseline. Note: Master's thesis, not peer-reviewed.
https://arxiv.org/abs/2511.11788
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