Agentic Task on ALFWorld Unseen
88.1Success Rate (SR)ExpGraph
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ExpGraphExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM)2026.05 | 88.1 | 17 | |
| IRCoTExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 87.3 | 19.6 | |
| ReasoningBankExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 81.3 | 24.1 | |
| AWMExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 80.6 | 18.8 | |
| S3Executor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 80.6 | 21.5 | |
| Search-o1Executor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 79.4 | 23.5 | |
| ExpGraphExecutor LLM=Qwen3-32B (Small LLM)2026.05 | 75.4 | 18 | |
| MemRLExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 71.6 | 26.1 | |
| LightMemExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 70.9 | 27.8 | |
| No-MemoryExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=No-Memory2026.05 | 64.9 | 26.3 | |
| ReActExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Prompt-based Agentic Baselines2026.05 | 63.4 | 25.1 | |
| ExpeLExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 63.4 | 28.7 | |
| Mem0Executor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 63.4 | 22.4 | |
| ReflexionExecutor LLM=Gemini-3.1-Flash-Lite (Large LLM), Method Strategy Category=Prompt-based Agentic Baselines2026.05 | 60.4 | 23.7 | |
| ReActExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Prompt-based Agentic Baselines2026.05 | 47 | 38.6 | |
| S3Executor LLM=Qwen3-32B (Small LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 42.5 | 22.5 | |
| ReflexionExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Prompt-based Agentic Baselines2026.05 | 40.3 | 38.7 | |
| No-MemoryExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=No-Memory2026.05 | 35.8 | 42.5 | |
| AWMExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 32.8 | 40.1 | |
| ExpeLExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 29.1 | 41.4 | |
| IRCoTExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 27.6 | 40.6 | |
| ReasoningBankExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 26.1 | 42.6 | |
| LightMemExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 25 | 39.2 | |
| MemRLExecutor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 20.2 | 49.6 | |
| Mem0Executor LLM=Qwen3-32B (Small LLM), Method Strategy Category=Retrieval-Centric Experience Learning Baselines2026.05 | 18.7 | 42.8 | |
| Search-o1Executor LLM=Qwen3-32B (Small LLM), Method Strategy Category=LLM-Centric Experience Learning Baselines2026.05 | 11.2 | 47.3 |