research
The Language Model Writes the Puzzle. The Solver Proves It.
A neuro-symbolic system translates Zebra puzzles into exact-cover tool calls, then uses solver feedback to repair incomplete or contradictory encodings.
Summary
A neuro-symbolic system translates Zebra puzzles into exact-cover tool calls, then uses solver feedback to repair incomplete or contradictory encodings.
Language models can parse natural clues but do not inherit the soundness and completeness of a symbolic solver. This framework asks a model to convert entities and constraints from a Zebra-style puzzle into structured calls that build an exact-cover instance. The solver computes the answer and returns feedback when the encoding is invalid, underconstrained or overconstrained; the system can then revise the translation, using the puzzle's promised uniqueness as an additional signal. Across multiple model sizes, post-training methods and families, the authors report consistent gains over chain-of-thought prompting and tested neuro-symbolic baselines. The guarantee applies to the exact-cover solution after a correct encoding, not to every semantic interpretation produced by the model.
Why it matters
A neuro-symbolic system translates Zebra puzzles into exact-cover tool calls, then uses solver feedback to repair incomplete or contradictory encodings.
Limits and context
- Language models can parse natural clues but do not inherit the soundness and completeness of a symbolic solver.
- The guarantee applies to the exact-cover solution after a correct encoding, not to every semantic interpretation produced by the model.
Key claims
A neuro-symbolic system translates Zebra puzzles into exact-cover tool calls, then uses solver feedback to repair incomplete or contradictory encodings.
Qualification: Language models can parse natural clues but do not inherit the soundness and completeness of a symbolic solver.
Evidence: source-2026-11-03-006
Sources
- arXiv preprint 2611.03641, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.