Graph Reasoning on G-Real
100Success RateAgentSquare
Evaluation Results
| Method | Links | |
|---|---|---|
| AgentSquareBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.05 | 100 | |
| FixedSolverBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.05 | 79.5 | |
| w/o Protocol-Reliability ObjBase LLM=gpt-5.4-nano, Ablation=w/o Protocol-Reliability Obj2026.05 | 79.5 | |
| EGL-SCA (Full)Base LLM=gpt-5.4-nano2026.05 | 79.5 | |
| w/o SCA RoutingBase LLM=gpt-5.4-nano, Ablation=w/o SCA Routing2026.05 | 78 | |
| w/o Instruction Evol.Base LLM=gpt-5.4-nano, Ablation=w/o Instruction Evol.2026.05 | 76 | |
| MA-GTSBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.05 | 72 | |
| w/o Tool GrowthBase LLM=gpt-5.4-nano, Ablation=w/o Tool Growth2026.05 | 69.5 | |
| ReActBase LLM=gpt-5.4-nano, Category=Tool-Augmented Agents, Tool Access=Fixed Toolbox2026.05 | 19.5 | |
| Few-ShotBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.05 | 6.5 | |
| ReflexionBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.05 | 5.5 | |
| ExpeLBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.05 | 5.5 | |
| w/o Tool UseBase LLM=gpt-5.4-nano, Ablation=w/o Tool Use2026.05 | 3 | |
| Chain-of-Thought (CoT)Base LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.05 | 2 | |
| Direct PromptingBase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.05 | 1.5 | |
| GEPABase LLM=gpt-5.4-nano, Category=Prompting & Self-Improvement, Tool Access=No Tools2026.05 | 0 |