AI
Neurosymbolic Routing for Reliable Reasoning on Resource-Constrained Edge Devices
Publication: cs.AI updates on arXiv.org
Author: Avyay Sadhu, Alvaro Velasquez, Lekai Chen
Source published: 30/09/2026, 04:00:00 UTC
Briefing created: 30/09/2026, 04:15:05 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 30/09/2026, 04:03:24 UTC.
Briefings
This research proposes a neurosymbolic router for edge devices that classifies queries to dispatch them to deterministic solvers or a small language model. Evaluated on 100 untested prompts from DeepMind Mathematics, GSM8K, and RuleTaker on a Raspberry Pi 4B, the system achieved 100% routing accuracy and 98.3% overall accuracy with a 512-token reasoning budget. It outperformed the strongest agent baseline (Program-of-Thought) by 21.3% and a tool-calling agent by 39.3%, while running 8.8x faster and 2.8x more energy-efficient than Program-of-Thought. The router uses an L* grammatical inference algorithm to learn a deterministic finite automaton, avoiding probabilistic models for structured tasks.
Key points
- The system uses an L* grammatical inference algorithm to learn a deterministic finite automaton (DFA) that classifies incoming queries.
- On a Raspberry Pi 4B with 8 GB RAM, the router achieved 100% routing accuracy and 98.3% overall accuracy on 100 untested prompts.
Context and limitations
Evaluation was limited to 100 untested prompts from DeepMind Mathematics, GSM8K, and RuleTaker on a single Raspberry Pi 4B device without GPU acceleration.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 30/09/2026, 04:15:05 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeid6vnhx3jbmohfaxlpwbbgc4n6ogbpclnlo2k3xnftjtjq6fxtgea