X

research csiro au

Bing Rank
Average Position of Bing Search Engine Ranking of related query such as 'Sales AI Agent', 'Coding AI Agent', etc.
Google Rank
Average Position of Bing Search Engine Ranking of related query such as 'Sales AI Agent', 'Coding AI Agent', etc.

Last Updated: 2025-04-11

Information

Software Systems Search Connect with us on Facebook Connect with us on Instagram Connect with us on LinkedIn Hear our our Spotify playlists Threads Watch our youtube videos Loading Comments... Summary: The tool/agent registry maintains a unified and convenient source to select diverse agents and tools. Context: Within an agent, the task executor may cooperate with other agents or leverage external tools for expanded capabilities. Problem: There are diverse agents and tools, how can the agent efficiently select the appropriate external agents and tools? Forces: Solution: Fig. 1 depicts how can an agent search external agents and tools via a tool/agent registry. A user prompts goals to an agent, which then decomposes the goals into fine-grained tasks. The agent can query the tool/agent registry, which is the main entry point for collecting and categorising various tools and agents regarding a series of metrics (e.g., capability, price, context window). Based on the returned information, the agent can employ and assign the tasks to respective tools and agents. Please note that a registry can be implemented in different manners, for instance, a coordinator agent with specific knowledge base, blockchain-based smart contract, etc., and a registry can be extended into a marketplace for tool/agent service trading. Figure 1. Tool/agent registry. Benefits: Drawbacks: Known uses: Related patterns: References: [1] J. Ruan, Y. Chen, B. Zhang, Z. Xu, T. Bao, du qing, shi shiwei, H. Mao, X. Zeng, and R. Zhao, “TPTU: Task planning and tool usage of large language model-based AI agents,” in NeurIPS 2023 Foundation Models for Decision Making Workshop, 2023. [Online]. Available: https://openreview.net/forum?id=GrkgKtOjaH [2] G. Wang, Y. Xie, Y. Jiang, A. Mandlekar, C. Xiao, Y. Zhu, L. Fan, and A. Anandkumar, “Voyager: An open-ended embodied agent with large language models,” in Intrinsically-Motivated and Open-Ended Learning Workshop @NeurIPS2023, 2023. [Online]. Available: https://openreview.net/forum?id=nfx5IutEed [3] T. Xie, F. Zhou, Z. Cheng, P. Shi, L. Weng, Y. Liu, T. J. Hua, J. Zhao, Q. Liu, C. Liu et al., “Openagents: An open platform for language agents in the wild,” arXiv preprint arXiv:2310.10634, 2023. We are committed to child safety and to the implementation of Child Safe principles and procedures. CSIRO acknowledges the Traditional Owners of the land, sea and waters, of the area that we live and work on across Australia. We acknowledge their continuing connection to their culture and pay our respects to their Elders past and present. View our vision towards reconciliation.

Prompts

Reviews

Tags

Write Your Review

Detailed Ratings

ALL
Correctness
Helpfulness
Interesting
Upload Pictures and Videos