DSP enables neural networks to perform constraint reasoning with learned feasibility signals, achieving 97.4% accuracy on planning tasks under 4x size generalization while maintaining balanced performance on feasible and infeasible cases.
Differentiable Symbolic Planning Module with Global Feasibility Aggregation and Sparse Attention for Neural Constraint Reasoning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility
DSP enables neural networks to perform constraint reasoning with learned feasibility signals, achieving 97.4% accuracy on planning tasks under 4x size generalization while maintaining balanced performance on feasible and infeasible cases.