📚 Sources

• Brown et al. — Language Models are Few-Shot Learners (GPT-3, 2020).
• Wei et al. — Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (2022).
• Kojima et al. — Large Language Models are Zero-Shot Reasoners (“Let’s think step by step,” 2022).
• Yao et al. — Tree of Thoughts: Deliberate Problem Solving with LLMs (NeurIPS 2023).
• Besta et al. — Graph of Thoughts: Solving Elaborate Problems with LLMs (2023).
• 2025 research on the redundancy of explicit CoT with reasoning models (inference-time reasoning, OpenAI o1 and successors) — an active area.
• Vendor product documentation and communications from OpenAI, Anthropic, Google (mid-2026 states) for engine names and their strengths. ⚠️ Versions and rankings evolve every 2-3 months; assistant comparisons are illustrative, to double-check at the time of reading.