{"version":1,"type":"story","url":"https://digestai.news/story/researchers-build-neurosymbolic-router-that-sends-math-to-exact-solver","json":"https://digestai.news/story/researchers-build-neurosymbolic-router-that-sends-math-to-exact-solver.json","markdown":"https://digestai.news/story/researchers-build-neurosymbolic-router-that-sends-math-to-exact-solver.md","slug":"researchers-build-neurosymbolic-router-that-sends-math-to-exact-solver","headline":"Researchers build neurosymbolic router that sends math to exact solvers on Raspberry Pi","summary":"A paper on arXiv describes a neurosymbolic router that classifies incoming queries and routes structured tasks such as arithmetic and logic to deterministic solvers, while sending open-ended word problems to a small language model. The router is a learned deterministic finite automaton trained with the L* grammatical inference algorithm, using the SLM as a membership oracle and labeled data as an equivalence oracle.\n\nOn a Raspberry Pi 4B with 8 GB RAM and no GPU, the system was tested on 100 unseen prompts from DeepMind Mathematics, GSM8K, and RuleTaker. It achieved 100% routing accuracy and 98.3% overall accuracy with a 512-token budget, compared with 72.0% for a Program-of-Thought baseline and 58.7% for a tool-calling agent. Formatted queries are answered in 1-11 ms, and a 30-token configuration runs 8.8x faster and 2.8x more energy-efficiently than Program-of-Thought.","keyPoints":["Router learns a DFA with L* algorithm to dispatch queries to exact solvers or SLM","98.3% overall accuracy on 100 test prompts, versus 72% for Program-of-Thought baseline","Runs 8.8x faster and 2.8x more energy-efficient on Raspberry Pi 4B (8 GB, no GPU)"],"whyItMatters":"Shows small edge devices can achieve high reasoning accuracy by offloading deterministic tasks to symbolic solvers, reducing reliance on large models.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["DeepMind","Raspberry Pi"],"models":[],"people":[]},"firstPublishedAt":"2026-09-30T04:00:00Z","updatedAt":"2026-09-30T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"Neurosymbolic Routing for Reliable Reasoning on Resource-Constrained Edge Devices","url":"https://arxiv.org/abs/2609.35833","publishedAt":"2026-09-30T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers build neurosymbolic router that sends math to exact solvers on Raspberry Pi\", 30 September 2026, https://digestai.news/story/researchers-build-neurosymbolic-router-that-sends-math-to-exact-solver","publisher":"Digest AI","title":"Researchers build neurosymbolic router that sends math to exact solvers on Raspberry Pi","datePublished":"2026-09-30T04:00:00Z","url":"https://digestai.news/story/researchers-build-neurosymbolic-router-that-sends-math-to-exact-solver"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}