Investigating Human--AI Discrepancies via Multiple-Solution Problems

cs.CY, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Comments: 50 pages, 16 pdf figures

Project page: https://hai-discrepancies.github.io

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

Sources

• ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
• Riemann-Bench: A Benchmark for Moonshot Mathematics
• iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs
• LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
• OpenAI GPT-5 System Card

Related papers

• Reasoning Enhances Robustness to Prompt Injection in LLM-Based Consensus
• Generative AI Purpose-built for Social and Mental Health: A Real-World Pilot
• PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks
• What is an intelligent system?
• AI University: An LLM-Powered Learning Assistant for Engineering---A Finite Element Method Case Study
• Generative AI Use in Entrepreneurship: An Integrative Review and an Empowerment-Entrapment Framework