CoMet couples a hypothesis-testing metaphor reasoner with a self-improving metaphor generator, and the resulting LLM agents win more often in metaphor-heavy language games.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games
CoMet couples a hypothesis-testing metaphor reasoner with a self-improving metaphor generator, and the resulting LLM agents win more often in metaphor-heavy language games.