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

This work addresses the problem of long-horizon task planning with the LargeLanguage Model (LLM) in an open-world household environment. Existing worksfail to explicitly track key objects and attributes, leading to erroneousdecisions in long-horizon tasks, or rely on highly engineered state featuresand feedback, which is not generalizable. We propose a novel, expandable staterepresentation that provides continuous expansion and updating of objectattributes from the LLM's inherent capabilities for context understanding andhistorical action reasoning. Our proposed representation maintains acomprehensive record of an object's attributes and changes, enabling robustretrospective summary of the sequence of actions leading to the current state.This allows enhanced context understanding for decision-making in taskplanning. We validate our model through experiments across simulated andreal-world task planning scenarios, demonstrating significant improvements overbaseline methods in a variety of tasks requiring long-horizon state trackingand reasoning.

LLM-State: Expandable State Representation for Long-horizon Task Planning in the Open World