Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.11303 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909957638586368 |
|---|---|
| author | Liu, Jiarun Xu, Shiyue Li, Yang Liu, Shangkun Yu, Yongli Cao, Peng |
| author_facet | Liu, Jiarun Xu, Shiyue Li, Yang Liu, Shangkun Yu, Yongli Cao, Peng |
| contents | Large Language Model agents face fundamental challenges in adapting to novel tasks due to limitations in tool availability and experience reuse. Existing approaches either rely on predefined tools with limited coverage or build tools from scratch without leveraging past experiences, leading to inefficient exploration and suboptimal performance. We introduce SMITH (Shared Memory Integrated Tool Hub), a unified cognitive architecture that seamlessly integrates dynamic tool creation with cross-task experience sharing through hierarchical memory organization. SMITH organizes agent memory into procedural, semantic, and episodic components, enabling systematic capability expansion while preserving successful execution patterns. Our approach formalizes tool creation as iterative code generation within controlled sandbox environments and experience sharing through episodic memory retrieval with semantic similarity matching. We further propose a curriculum learning strategy based on agent-ensemble difficulty re-estimation. Extensive experiments on the GAIA benchmark demonstrate SMITH's effectiveness, achieving 81.8% Pass@1 accuracy and outperforming state-of-the-art baselines including Alita (75.2%) and Memento (70.9%). Our work establishes a foundation for building truly adaptive agents that continuously evolve their capabilities through principled integration of tool creation and experience accumulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11303 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecture Liu, Jiarun Xu, Shiyue Li, Yang Liu, Shangkun Yu, Yongli Cao, Peng Computation and Language Large Language Model agents face fundamental challenges in adapting to novel tasks due to limitations in tool availability and experience reuse. Existing approaches either rely on predefined tools with limited coverage or build tools from scratch without leveraging past experiences, leading to inefficient exploration and suboptimal performance. We introduce SMITH (Shared Memory Integrated Tool Hub), a unified cognitive architecture that seamlessly integrates dynamic tool creation with cross-task experience sharing through hierarchical memory organization. SMITH organizes agent memory into procedural, semantic, and episodic components, enabling systematic capability expansion while preserving successful execution patterns. Our approach formalizes tool creation as iterative code generation within controlled sandbox environments and experience sharing through episodic memory retrieval with semantic similarity matching. We further propose a curriculum learning strategy based on agent-ensemble difficulty re-estimation. Extensive experiments on the GAIA benchmark demonstrate SMITH's effectiveness, achieving 81.8% Pass@1 accuracy and outperforming state-of-the-art baselines including Alita (75.2%) and Memento (70.9%). Our work establishes a foundation for building truly adaptive agents that continuously evolve their capabilities through principled integration of tool creation and experience accumulation. |
| title | Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecture |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2512.11303 |