List your company

Graph Reasoning on NLGraph

97Success RateEGL-SCA (Full)
11.7233.865678.14May 11, 2026

Evaluation results

MethodLinks
EGL-SCA (Full)Base LLM=gpt-5.4-nano2026.0597
w/o Protocol-Reliability ObjBase LLM=gpt-5.4-nano, Ablation=w/o Protocol-Reliability Obj2026.0594.5
w/o SCA RoutingBase LLM=gpt-5.4-nano, Ablation=w/o SCA Routing2026.0593
w/o Tool GrowthBase LLM=gpt-5.4-nano, Ablation=w/o Tool Growth2026.0593
w/o Instruction Evol.Base LLM=gpt-5.4-nano, Ablation=w/o Instruction Evol.2026.0588.5
AgentSquareBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.0563.5
MA-GTSBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.0562.9
ReActBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.0559
FixedSolverBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.0558
w/o Tool UseBase LLM=gpt-5.4-nano, Ablation=w/o Tool Use2026.0544.5
Chain-of-Thought (CoT)Base LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.0530
Direct PromptingBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.0524.5
GEPABase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.0521.5
ExpeLBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.0521
ReflexionBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.0517
Few-ShotBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.0515