DEPT detects training impasses in social language agents via dual-scale divergence and entropy, then uses asymmetric reshaping to restore exploration gradients and prevent policy homogenization.
- By rejecting , Player 1 maintains the option to propose a better deal in the next round or wait for Player 0 to make a more fair offer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents
DEPT detects training impasses in social language agents via dual-scale divergence and entropy, then uses asymmetric reshaping to restore exploration gradients and prevent policy homogenization.