Reconstructing the exact model invocation state for each sampled action, instead of flattening the whole interaction, lets teacher distillation guide compact-memory agents without state mismatch.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MemOPD: On-Policy Distillation through Memory State Alignment for Long-Horizon Agents
Reconstructing the exact model invocation state for each sampled action, instead of flattening the whole interaction, lets teacher distillation guide compact-memory agents without state mismatch.