List your company

Graph Reasoning on G-Real

100Success RateAgentSquare
-4235077May 11, 2026

Evaluation results

MethodLinks
AgentSquareBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.05100
FixedSolverBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.0579.5
w/o Protocol-Reliability ObjBase LLM=gpt-5.4-nano, Ablation=w/o Protocol-Reliability Obj2026.0579.5
EGL-SCA (Full)Base LLM=gpt-5.4-nano2026.0579.5
w/o SCA RoutingBase LLM=gpt-5.4-nano, Ablation=w/o SCA Routing2026.0578
w/o Instruction Evol.Base LLM=gpt-5.4-nano, Ablation=w/o Instruction Evol.2026.0576
MA-GTSBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.0572
w/o Tool GrowthBase LLM=gpt-5.4-nano, Ablation=w/o Tool Growth2026.0569.5
ReActBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.0519.5
Few-ShotBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.056.5
ReflexionBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.055.5
ExpeLBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.055.5
w/o Tool UseBase LLM=gpt-5.4-nano, Ablation=w/o Tool Use2026.053
Chain-of-Thought (CoT)Base LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.052
Direct PromptingBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.051.5
GEPABase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.050