Agentic Task on ExpSuite-Agentic Aggregated
62.3ScoreExpGraph
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ExpGraphExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM)2026.05 | 62.3 | 15.2 | |
| S3Executor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 55.3 | 21.1 | |
| Search-o1Executor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 54.3 | 23.3 | |
| ExpGraphExecutor LLM=Qwen3-32B (Small LLM)2026.05 | 53.4 | 14.4 | |
| ReasoningBankExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 52.5 | 25.4 | |
| IRCoTExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 52 | 23.4 | |
| AWMExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 49.7 | 23.6 | |
| ExpeLExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 44.6 | 25.8 | |
| MemRLExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 44.6 | 19.5 | |
| ReflexionExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Prompt-based Agentic Baselines2026.05 | 44.2 | 19.4 | |
| S3Executor LLM=Qwen3-32B (Small LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 44 | 16.5 | |
| LightMemExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 43.6 | 31.6 | |
| ReActExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Prompt-based Agentic Baselines2026.05 | 42.6 | 20.5 | |
| No-MemoryExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=No-Memory2026.05 | 38.3 | 32.9 | |
| IRCoTExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 37.6 | 23.4 | |
| Mem0Executor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 36.9 | 31.5 | |
| ExpeLExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 32.3 | 30.2 | |
| MemRLExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 30.2 | 29.9 | |
| LightMemExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 29 | 35.8 | |
| ReActExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Prompt-based Agentic Baselines2026.05 | 28.9 | 33.8 | |
| Search-o1Executor LLM=Qwen3-32B (Small LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 28.7 | 23.7 | |
| AWMExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 27.8 | 33.7 | |
| ReflexionExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Prompt-based Agentic Baselines2026.05 | 26.9 | 34.6 | |
| ReasoningBankExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 26.8 | 29.2 | |
| No-MemoryExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=No-Memory2026.05 | 25.1 | 34.7 | |
| Mem0Executor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 19.5 | 36.4 |