Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909335049732096 |
|---|---|
| author | Gu, Yu Shu, Yiheng Yu, Hao Liu, Xiao Dong, Yuxiao Tang, Jie Srinivasa, Jayanth Latapie, Hugo Su, Yu |
| author_facet | Gu, Yu Shu, Yiheng Yu, Hao Liu, Xiao Dong, Yuxiao Tang, Jie Srinivasa, Jayanth Latapie, Hugo Su, Yu |
| contents | The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist agents capable of operating within complex environments. These environments are often highly expansive, making it impossible for the LLM to process them within its short-term memory. Motivated by recent research on extending the capabilities of LLMs with tools, we seek to investigate the intriguing potential of tools to augment LLMs in handling such complexity by introducing a novel class of tools, termed middleware, to aid in the proactive exploration within these massive environments. Such specialized tools can serve as a middleware layer shielding the LLM from environmental complexity. In two representative complex environments -- knowledge bases (KBs) and databases -- we demonstrate the significant potential of augmenting language agents with tools in complex environments. Notably, equipped with the middleware, GPT-4 achieves 2.8X the performance of the best baseline in tasks requiring access to database content and 2.2X in KB tasks. Our findings illuminate the path for advancing language agents in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14672 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments Gu, Yu Shu, Yiheng Yu, Hao Liu, Xiao Dong, Yuxiao Tang, Jie Srinivasa, Jayanth Latapie, Hugo Su, Yu Computation and Language Artificial Intelligence I.2.7 The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist agents capable of operating within complex environments. These environments are often highly expansive, making it impossible for the LLM to process them within its short-term memory. Motivated by recent research on extending the capabilities of LLMs with tools, we seek to investigate the intriguing potential of tools to augment LLMs in handling such complexity by introducing a novel class of tools, termed middleware, to aid in the proactive exploration within these massive environments. Such specialized tools can serve as a middleware layer shielding the LLM from environmental complexity. In two representative complex environments -- knowledge bases (KBs) and databases -- we demonstrate the significant potential of augmenting language agents with tools in complex environments. Notably, equipped with the middleware, GPT-4 achieves 2.8X the performance of the best baseline in tasks requiring access to database content and 2.2X in KB tasks. Our findings illuminate the path for advancing language agents in real-world applications. |
| title | Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments |
| topic | Computation and Language Artificial Intelligence I.2.7 |
| url | https://arxiv.org/abs/2402.14672 |