HyMeS separates motor control from memory management by steering a frozen neural policy with a learned symbolic program, lifting task success from 41.3% to 60.1% on a 12-task memory benchmark.
arXiv:2603.04466
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation
HyMeS separates motor control from memory management by steering a frozen neural policy with a learned symbolic program, lifting task success from 41.3% to 60.1% on a 12-task memory benchmark.