RESEARCH · RESEARCH · #1261
Neurosymbolic router learns DFA to route edge queries, improving small-model accuracy and efficiency
arXiv:2609.35833v1 proposes a neurosymbolic router that classifies incoming queries and dispatches them to the cheapest correct solver, learning a deterministic finite automaton (DFA) with the L* algorithm using a small language model as a membership oracle. On a Raspberry Pi 4B evaluated on 100 unseen prompts from DeepMind Mathematics, GSM8K, and RuleTaker, the learned router achieves 100% routing accuracy and 98.3% overall accuracy with a 512-token reasoning budget (93.3% on word problems), outperforming Program-of-Thought (72.0%) and a tool-calling agent (58.7%), while answering formatted queries in 1–11 ms and, in a 30-token configuration, running 8.8× faster and 2.8× more energy-efficient than Program-of-Thought.
KEY POINTS
- arXiv:2609.35833v1 proposes a neurosymbolic router that classifies incoming queries and dispatches them to the cheapest correct solver, learning a deterministic finite automaton (DFA) with the L* algorithm using a small language model as a membership oracle.
- On a Raspberry Pi 4B evaluated on 100 unseen prompts from DeepMind Mathematics, GSM8K, and RuleTaker, the learned router achieves 100% routing accuracy and 98.3% overall accuracy with a 512-token reasoning budget (93.3% on word problems), outperforming Program-of-Thought (72.0%) and a tool-calling agent (58.7%), while answering formatted queries in 1–11 ms and, in a 30-token configuration, running 8.8× faster and 2.8× more energy-efficient than Program-of-Thought.
- This approach lets tiny, offline language models avoid costly probabilistic approximations for structurally deterministic tasks by routing them to exact symbolic solvers, substantially boosting accuracy and energy efficiency for edge deployment.
WHY IT MATTERS
This approach lets tiny, offline language models avoid costly probabilistic approximations for structurally deterministic tasks by routing them to exact symbolic solvers, substantially boosting accuracy and energy efficiency for edge deployment.