Learning to Use Tools via Cooperative and Interactive Agents
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_ | 1866909229176061952 |
|---|---|
| author | Shi, Zhengliang Gao, Shen Chen, Xiuyi Feng, Yue Yan, Lingyong Shi, Haibo Yin, Dawei Ren, Pengjie Verberne, Suzan Ren, Zhaochun |
| author_facet | Shi, Zhengliang Gao, Shen Chen, Xiuyi Feng, Yue Yan, Lingyong Shi, Haibo Yin, Dawei Ren, Pengjie Verberne, Suzan Ren, Zhaochun |
| contents | Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. Existing methods employ one single LLM-based agent to iteratively select and execute tools, thereafter incorporating execution results into the next action prediction. Despite their progress, these methods suffer from performance degradation when addressing practical tasks due to: (1) the pre-defined pipeline with restricted flexibility to calibrate incorrect actions, and (2) the struggle to adapt a general LLM-based agent to perform a variety of specialized actions. To mitigate these problems, we propose ConAgents, a Cooperative and interactive Agents framework, which coordinates three specialized agents for tool selection, tool execution, and action calibration separately. ConAgents introduces two communication protocols to enable the flexible cooperation of agents. To effectively generalize the ConAgents into open-source models, we also propose specialized action distillation, enhancing their ability to perform specialized actions in our framework. Our extensive experiments on three datasets show that the LLMs, when equipped with the ConAgents, outperform baselines with substantial improvement (i.e., up to 14% higher success rate). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_03031 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning to Use Tools via Cooperative and Interactive Agents Shi, Zhengliang Gao, Shen Chen, Xiuyi Feng, Yue Yan, Lingyong Shi, Haibo Yin, Dawei Ren, Pengjie Verberne, Suzan Ren, Zhaochun Computation and Language Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. Existing methods employ one single LLM-based agent to iteratively select and execute tools, thereafter incorporating execution results into the next action prediction. Despite their progress, these methods suffer from performance degradation when addressing practical tasks due to: (1) the pre-defined pipeline with restricted flexibility to calibrate incorrect actions, and (2) the struggle to adapt a general LLM-based agent to perform a variety of specialized actions. To mitigate these problems, we propose ConAgents, a Cooperative and interactive Agents framework, which coordinates three specialized agents for tool selection, tool execution, and action calibration separately. ConAgents introduces two communication protocols to enable the flexible cooperation of agents. To effectively generalize the ConAgents into open-source models, we also propose specialized action distillation, enhancing their ability to perform specialized actions in our framework. Our extensive experiments on three datasets show that the LLMs, when equipped with the ConAgents, outperform baselines with substantial improvement (i.e., up to 14% higher success rate). |
| title | Learning to Use Tools via Cooperative and Interactive Agents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.03031 |