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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Pre-trained large language models (LLMs) capture procedural knowledge aboutthe world. Recent work has leveraged LLM's ability to generate abstract plansto simplify challenging control tasks, either by action scoring, or actionmodeling (fine-tuning). However, the transformer architecture inherits severalconstraints that make it difficult for the LLM to directly serve as the agent:e.g. limited input lengths, fine-tuning inefficiency, bias from pre-training,and incompatibility with non-text environments. To maintain compatibility witha low-level trainable actor, we propose to instead use the knowledge in LLMs tosimplify the control problem, rather than solving it. We propose the Plan,Eliminate, and Track (PET) framework. The Plan module translates a taskdescription into a list of high-level sub-tasks. The Eliminate module masks outirrelevant objects and receptacles from the observation for the currentsub-task. Finally, the Track module determines whether the agent hasaccomplished each sub-task. On the AlfWorld instruction following benchmark,the PET framework leads to a significant 15% improvement over SOTA forgeneralization to human goal specifications.

Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents