List your company
ResearchFormerly WizWand

Multi-agent system task solving on finance

76.7AccuracyTacoMAS
26.46839.50952.5565.591May 10, 2026
Updated 5mo ago

Evaluation results

MethodLinks
TacoMASEvolution Time Scale=Topology-capability co-evolution, Base LLM=Gemini-2.5-flash-lite, Meta-LLM=Gemini-2.5-pro, Rubric Judge=GPT-4o-mini2026.0576.7
SASEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0553.9
MAS-HybridEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0553.7
MAS-IndependentEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0552.9
MAS-CentralizedEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0550
MAS-DecentralizedEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0544.5
MetaGenEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0541.9
CORALEvolution Time Scale=Within-instance evolution, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0540.9
SelfOrgEvolution Time Scale=Within-instance evolution, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0537.7
MetaAgentEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0534.9
MetaGPTEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0534.8
AFlowEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0534.3
ChatDev-PuppeteerEvolution Time Scale=Within-instance evolution, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0534
SwarmAgenticEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0533.8
EvolveRouterEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0533.2
EvoAgentXEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0531.3
AgentVerseEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0530.1
ARG-DesignerEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0529.5
ADASEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0529.4
AgentSquareEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0528.6
MaASEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0528.4