03 Prompting and Context 3 min read 650 words

Chain-of-Thought (CoT)

Chain-of-Thought (CoT) is the technique of encouraging an LLM to generate intermediate reasoning steps before providing a final answer. In late 2025, this has evolved from a simple prompt phrase to the CORE architectural feature of reasoning models.

promptingreasoningcore
01revolution

The CoT Revolution

Standard LLMs are "Next Token Predictors." For complex math or logic, a single pass is often insufficient. CoT provides the "Scribble Pad" (Working Memory) for the model to work through sub-problems.

The Formula: Input -> Reasoning (Chain) -> Output

02programmatic cot

Zero-Shot vs. Programmatic CoT

TechniqueTrigger PhraseEfficiencyUse Case
Zero-Shot CoT"Let's think step by step."HighAd-hoc queries.
Few-Shot CoT(Provided examples with logic)Higher StabilityProduction pipelines.
Programmatic CoT"1. Analyze X. 2. Verify Y. 3. Resolve Z."Best for AgentsComplex multi-tool tasks.
03models dec

The Rise of "Thinking" Models (Dec 2025)

Models like OpenAI o1 and DeepSeek-R1 have CoT "baked in" via Reinforcement Learning (RL).

  1. System-Level CoT: The model doesn't just "print" reasoning; it has a dedicated "Thinking Window."
  2. Hidden CoT: In many enterprise versions, the reasoning chain is hidden from the user but verifiable by the system to prevent prompt injection or "thought leakage."
  3. Scaling Law: These models follow the Inference Scaling Law—the longer they "think," the better they solve hard problems ($o1$ can solve gold-medal IMO math given enough time).
04verification

Self-Correction and Verification

In 2025, we no longer trust a single Chain-of-Thought. We use Self-Verification.

Markdownmarkdown · 4 lines
1234
# Process
1. Generate Answer A via CoT.
2. Critique: "Are there any errors in the logic above?"
3. If errors: "Correct the logic and provide Answer B."

The 2025 Nuance: This is now integrated into Execution-Verified CoT for coding, where the model writes the logic, runs the code, and corrects itself if the code fails.

05fails over-thinking

When CoT Fails (Over-thinking)

CoT is not a silver bullet. For simple tasks, it adds:

  1. Latency: More tokens = slower response.
  2. Cost: You pay for every "thought" token.
  3. Over-thinking: The model might hallucinate complexity where none exists (e.g., explaining why 2+2=4 for 3 paragraphs).
06questions

Interview Questions

Q: Why does CoT improve performance on mathematical word problems?

Strong answer: CoT improves performance by aligning the model's computational complexity with the task's logical complexity. In a standard single-pass generation, the model must predict the final answer token based on limited local information. With CoT, the model "breaks" the problem into smaller, auto-regressive steps. Each step uses the previous step's output as context, allowing the model's attention mechanism to focus on one sub-problem at a time (e.g., first adding the apples, then subtracting the oranges), reducing the "cognitive load" of the single-pass prediction.

Q: How do you handle CoT in a production environment where latency is critical?

Strong answer: We use a Hybrid Reasoning Architecture:

  1. Tier 1 (Fast): A classifier identifies if the query needs deep reasoning.
  2. Tier 2 (Condensed CoT): We prompt the model with "Be concise in your reasoning," or use "Knowledge Distillation" where we train a smaller model to produce only the final answer while benefitting from a teacher's CoT-style pretraining.
  3. Tier 3 (Streaming): We stream the CoT to the user (if transparent) or a background process so the system can begin "pre-processing" the final result as it appears.
07references

References

  • Wei et al. "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models" (2022)
  • Wang et al. "Self-Consistency Improves Chain of Thought Reasoning in Language Models" (2023)
  • OpenAI. "Learning to Reason with LLMs" (2024)

Next: Tree-of-Thought

summary · added by this rebuild

Key takeaways

01

CoT is now architecture, not a phrase

Reasoning models bake the chain in through reinforcement learning with a dedicated thinking window, often hidden from the user but still verifiable by the surrounding system.

02

Three CoT styles, three jobs

Zero-shot "let's think step by step" for ad-hoc queries, few-shot examples for stable production pipelines, and numbered programmatic steps for multi-tool agent tasks.

03

Verify the chain, do not trust it

Self-verification generates an answer, critiques its own logic, then corrects; for code this becomes execution-verified CoT, where the model runs what it wrote and fixes failures.

04

Reasoning has a latency and cost floor

Every thought token is billed and waited on, and on simple questions models over-think — spending paragraphs justifying an answer a single pass would have produced.

05

Route reasoning instead of always paying

A fast classifier decides whether a query needs deep reasoning, leaving condensed-reasoning prompts or a distilled small model to handle everything below that bar.