A Reasoning-Based Approach to Cryptic Crossword Clue Solving
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Cryptic crossword clues are challenging language tasks for which new test sets are released daily by major newspapers on a global basis. Each cryptic clue contains both the definition of the answer to be placed in the crossword grid (in common with regular crosswords), and 'wordplay' that proves that the answer is correct (i.e. a human solver can be confident that an answer is correct without needing crossing words as confirmation). This work describes an LLM-based reasoning system built from open-licensed components that solves cryptic clues by (i) hypothesising answers; (ii) proposing wordplay explanations; and (iii) using a verifier system that operates on codified reasoning steps. Overall, this system establishes a new state-of-the-art performance on the challenging Cryptonite dataset of clues from The Times and The Telegraph newspapers in the UK. Because each proved solution is expressed in Python, interpretable wordplay reasoning for proven answers is available for inspection.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 5 of its 36 references that are in the map. First posted on arXiv 5 Jun 2025.
Builds on
5 of 36 references.
References · 5
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
- 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
- 2024Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineeringcited by 103
- 2024Are LLMs Good Cryptic Crossword Solvers?cited by 7
- 2024Language Models are Crossword Solverscited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025PUZZLED: Jailbreaking LLMs through Word-Based Puzzles
- 2022Down and Across: Introducing Crossword-Solving as a New NLP Benchmark
- 2026The Riddle Riddle: Testing Flexible Reasoning in Large Language Models and Humans
- 2026Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks
- 2024Puzzle Solving using Reasoning of Large Language Models: A Survey
- 2025FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving
- 2025CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
- 2024Solving Zebra Puzzles Using Constraint-Guided Multi-Agent Systems