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

Diverse evaluation benchmarks play a crucial role to assess a wide range ofcapabilities of large language models (LLM). Although plenty of endeavors havebeen dedicated to building valuable benchmarks, there is still little workaiming at evaluating the capability of LLM in multistep interactiveenvironments. Noticing that LLM requires a text representation of theenvironment observations for interaction, we choose to fill such a blank bybuilding a novel benchmark based on the information user interface (InfoUI).InfoUI consists of rich text contents and can be represented in some textformats, thus is suitable for the assessment of interaction ability of LLM.Additionally, the complex structures of InfoUI can further raise a challengefor LLM to understand structured texts rather than plain texts. An interactionplatform is always used to evaluate an agent, however, there is still a lack ofa satisfactory interaction platform dedicated to InfoUI. Consequently, wepropose to build a novel easily-extendable, adaptable, and close-to-realityinteraction platform, Mobile-Env, to provide a base for an appropriatebenchmark. Based on Mobile-Env, an InfoUI task set WikiHow is then built toestablish a benchmark for the multistep interaction capability of LLM instructured text-based environments. Agents based on a series of LLMs are testedon the task set to obtain an insight into the potential and challenge of LLMfor InfoUI interaction. It is sincerely welcome that the community contributenew environments and new task sets for Mobile-Env to provide better testbenchmarks and facilitate the development of the corresponding domains.

Mobile-Env: An Evaluation Platform and Benchmark for Interactive Agents in LLM Era