List your company
ResearchFormerly WizWand

Multi-agent system task solving on workbench

82.4AccuracyTacoMAS
26.86441.28255.770.118May 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-mini2026.0582.4
SwarmAgenticEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0565.1
ADASEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0564.5
ARG-DesignerEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0559.5
MaASEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0553.8
AgentVerseEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0552.3
CORALEvolution Time Scale=Within-instance evolution, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0551.1
MetaGenEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0549.2
AFlowEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0547.8
MetaGPTEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0547.3
MetaAgentEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0546.9
MAS-DecentralizedEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0544.6
ChatDev-PuppeteerEvolution Time Scale=Within-instance evolution, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0544.1
SelfOrgEvolution Time Scale=Within-instance evolution, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0544.1
AgentSquareEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0544
EvoAgentXEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0541.9
MAS-IndependentEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0541.6
MAS-CentralizedEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0538.6
MAS-HybridEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0538.6
SASEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0534.7
EvolveRouterEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0529