CoTu Achieves Top Technical Score at EXACT 2026 with Neuro-Symbolic QA System

Jul 17, 2026

Team CoTu developed a neuro-symbolic Program-of-Thought pipeline using a 4B-parameter model that generates Z3 or Python code instead of direct answers, achieving a perfect score on the physics task and the highest final-round technical score (13.44/15) at the EXACT 2026 competition. The system addresses logical reasoning over university regulations and multi-step physics problems within a 60-second latency limit using SGLang and speculative decoding. CoTu placed 3rd overall when including presentation scores.

Why it matters: This work demonstrates that small, open-weight models (≤8B) can achieve state-of-the-art reasoning accuracy by combining neural language models with symbolic solvers, offering a transparent and verifiable approach to educational QA.

Full story at: arXiv Computation and Language ↗