English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large Language Models (LLMs) have demonstrated proficiency in addressingtasks that necessitate a combination of task planning and the usage of externaltools that require a blend of task planning and the utilization of externaltools, such as APIs. However, real-world complex systems present threeprevalent challenges concerning task planning and tool usage: (1) The realsystem usually has a vast array of APIs, so it is impossible to feed thedescriptions of all APIs to the prompt of LLMs as the token length is limited;(2) the real system is designed for handling complex tasks, and the base LLMscan hardly plan a correct sub-task order and API-calling order for such tasks;(3) Similar semantics and functionalities among APIs in real systems createchallenges for both LLMs and even humans in distinguishing between them. Inresponse, this paper introduces a comprehensive framework aimed at enhancingthe Task Planning and Tool Usage (TPTU) abilities of LLM-based agents operatingwithin real-world systems. Our framework comprises three key componentsdesigned to address these challenges: (1) the API Retriever selects the mostpertinent APIs for the user task among the extensive array available; (2) LLMFinetuner tunes a base LLM so that the finetuned LLM can be more capable fortask planning and API calling; (3) the Demo Selector adaptively retrievesdifferent demonstrations related to hard-to-distinguish APIs, which is furtherused for in-context learning to boost the final performance. We validate ourmethods using a real-world commercial system as well as an open-sourcedacademic dataset, and the outcomes clearly showcase the efficacy of eachindividual component as well as the integrated framework.

TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems