EELMA estimates the mutual information between an LM agent's actions and future text states, and this 'empowerment' is shown to correlate with task performance across toy games and WebArena.
Empowerment for continuous agent--environment systems
1 Pith paper cite this work, alongside 82 external citations. Polarity classification is still indexing.
1
Pith paper citing it
82
external citations · OpenAlex
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Estimating the Empowerment of Language Model Agents
EELMA estimates the mutual information between an LM agent's actions and future text states, and this 'empowerment' is shown to correlate with task performance across toy games and WebArena.