Linear RNNs track states from REPL code traces of permutations better than Transformers, but non-linear RNNs outperform them in partially observable probabilistic automata.
Tracking world states with language models: State-based evaluation using chess
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning State-Tracking from Code Using Linear RNNs
Linear RNNs track states from REPL code traces of permutations better than Transformers, but non-linear RNNs outperform them in partially observable probabilistic automata.