List your company

Multi-agent system task solving on BrowseComp

74.5AccuracyTacoMAS
6.3824.06541.7559.435May 10, 2026

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-mini2026.0574.5
SelfOrgEvolution Time Scale=Within-instance evolution, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0568.8
AFlowEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0563.3
AgentSquareEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0562.5
AgentVerseEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0562.5
ARG-DesignerEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0562.1
MaASEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0562
ChatDev-PuppeteerEvolution Time Scale=Within-instance evolution, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0560.3
MetaAgentEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0560.1
ADASEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0559.5
EvoAgentXEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0559.1
SwarmAgenticEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0557
MetaGPTEvolution Time Scale=Offline-evolved, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0555
MetaGenEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0551.3
CORALEvolution Time Scale=Within-instance evolution, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0550.5
MAS-CentralizedEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0527
MAS-HybridEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0526
MAS-DecentralizedEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0524
SASEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0520
EvolveRouterEvolution Time Scale=Per-instance graph design, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.0517
MAS-IndependentEvolution Time Scale=Fixed-topology, Base LLM=Gemini-2.5-flash-lite, Rubric Judge=GPT-4o-mini2026.059