Beyond Memorization: Distinguishing Between Pattern-Based and Epistemic Reasoning in LLMs Using Epistemic Puzzles

arXiv:2603.21350 · cs.CL · Submitted 2026-03-22 · Read on arXiv

cs.CL

Submitted: 2026-03-22

Updated: 2026-09-07

Comments: Accepted to EMNLP 2026 main conference

Code: https://github.com/adigabay84/del-puzzles-benchmark

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 14× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Dynamic Epistemic Logic — 5× in this paper
• Core — 2× in this paper · explained in 2 episodes
• F1 Score — 2× in this paper · explained in 3 episodes
• Multi-Agent System — 2× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Mistral 7B
• Cooperative Epistemic Multi-Agent Planning for Implicit Coordination
• Gemini: A Family of Highly Capable Multimodal Models
• HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle Games
• ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering