Arthur Szlam, Kavya Srinet, Yuxuan Sun, Gabriel Synnaeve, Sainbayar Sukhbaatar, Jack Lanchantin
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent progress in using machine learning models for reasoning tasks has been driven by novel model architectures, large-scale pre-training protocols, and dedicated reasoning datasets for fine-tuning. In this work, to further pursue these advances, we introduce a new data generator for machine reasoning that integrates with an embodied agent. The generated data consists of templated text queries and answers, matched with world-states encoded into a database. The world-states are a result of both world dynamics and the actions of the agent. We show the results of several baseline models on instantiations of train sets. These include pre-trained language models fine-tuned on a text-formatted representation of the database, and graph-structured Transformers operating on a knowledgegraph representation of the database. We find that these models can answer some questions about the world-state, but struggle with others. These results hint at new research directions in designing neural reasoning models and database representations. Code to generate the data and train the models will be released at github.com/facebookresearch/neuralmemory.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2309.07974")
get_code_for_paper("2309.07974")
have("2309.07974")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2309.07974.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2309.07974)
Connect an agent — have() is free.