Google

Least-to-most prompting is a problem-solving technique for LLMs designed for difficult reasoning problems that cannot be solved by simply generalizing from a few examples. The core strategy is to break down a complex problem into a progressive sequence of simpler sub-problems. These sub-problems are then solved sequentially, systematically leading to the final conclusion. This method provides a foundational framework for generating and solving sub-problems, which can be further enhanced with more advanced prompting techniques.

Least-to-Most Prompting

Within the least-to-most prompting framework, the generation of sub-problems is accomplished by prompting a Large Language Model. This process can be guided by providing the LLM with specific instructions and/or demonstrations, such as few-shot examples, to effectively break down the larger problem.

Sub-problem Generation in Least-to-Most Prompting

The foundational framework of least-to-most prompting can be enhanced by integrating various advanced prompting strategies. This approach allows for performance improvements without needing to modify the core problem decomposition structure of the method.

Improving Least-to-Most Prompting with Advanced Techniques

Beyond applying advanced prompting techniques to existing sub-problems, the least-to-most method can also be improved by developing better methods for the initial problem decomposition and for organizing the subsequent problem-solving path.

Improving Problem Decomposition in Least-to-Most Prompting

An AI developer needs a large language model to solve a complex, multi-step logic puzzle that requires deducing a final answer from a series of interdependent clues. Initial attempts to solve the puzzle by providing the full puzzle and a few examples of other solved puzzles have consistently failed. Which of the following prompting strategies is the most effective next step, and why?

A developer is tasked with creating a system for a large language model to solve complex mathematical word problems. They implement a strategy where the model is first prompted to identify a simpler, solvable part of the problem. The model's answer to that simpler part is then included in the next prompt, which asks the model to solve the next logical piece of the problem. This continues until the final answer is reached. Analyze the primary strength of this problem-solving approach.

Analyzing a Problem-Solving Approach

Your team is rolling out an internal LLM assistant...

You’re building an internal LLM workflow to produc...

You’re building an internal LLM assistant to help ...

You’re leading an internal enablement team buildin...

You are deploying an LLM inside an internal finance tool that must answer multi-step policy questions (e.g., “Is this expense reimbursable given these 6 policy clauses and these 3 trip details?”). Constraints: (1) you have a strict context window budget, so you can include at most ONE short worked example in the prompt; (2) the model’s first-pass answers are often incomplete (it sometimes explains reasoning but forgets to state a final decision); (3) you need a workflow that is reliable across many different question shapes, not just one template.

Write an essay proposing a concrete prompting workflow that combines: in-context learning (if you use it), chain-of-thought prompting (including whether you would use zero-shot CoT), explicit problem decomposition (including whether you would use a least-to-most progression), and an iterative self-refinement loop. Your answer must (a) explain why your chosen combination fits the constraints, (b) describe the exact sequence of LLM calls or prompt sections you would use, (c) explain how intermediate sub-answers feed into later steps, and (d) specify how you will force a clear final decision despite the risk of incomplete zero-shot CoT outputs. Include at least two tradeoffs you are accepting (e.g., latency vs. accuracy, context budget vs. guidance, error propagation vs. transparency) and how you would mitigate them.

Choosing and Justifying a Prompting Strategy Under Context and Quality Constraints

You are deploying an LLM inside a corporate workflow to draft a first-pass analysis for a high-stakes internal decision memo (e.g., whether to approve a vendor contract). The input is a long, messy bundle of notes and constraints, and early pilots show two failure modes: (1) when asked directly, the model misses key constraints and produces confident but shallow conclusions; (2) when you add a generic “let’s think step by step” instruction, it produces lengthy reasoning but sometimes never states a clear final recommendation.

Write a proposed prompting workflow (you may describe it as a sequence of prompts) that uses: in-context learning with demonstrations, chain-of-thought prompting (including a zero-shot trigger where appropriate), least-to-most prompting, explicit problem decomposition, and an iterative self-refinement loop. Your answer must explain how these techniques work together (not independently) to reduce the two failure modes above, and must justify at least two tradeoffs you are making (e.g., latency/cost vs. accuracy, transparency vs. risk of overlong reasoning, fixed vs. dynamic decomposition). Conclude by giving one concrete example of a “final answer formatting” instruction you would include to ensure the model always outputs a clear recommendation at the end.

Designing a Prompting Workflow for a High-Stakes, Multi-Step Task

You are building an internal LLM assistant that helps a finance operations team investigate invoice-payment discrepancies. A typical ticket requires (a) extracting key entities from a messy email thread, (b) reconciling amounts across two systems, (c) identifying the most likely root cause (e.g., duplicate invoice, partial payment, currency conversion, timing), and (d) drafting a customer-facing explanation.

Your first implementation uses a single prompt with the full ticket text and the instruction “Let’s think step by step and give the final answer.” It often produces plausible reasoning but (1) misses a critical sub-check (e.g., currency conversion), (2) sometimes never states a clear final conclusion, and (3) varies in format so downstream automation breaks.

Write an essay that proposes a revised prompting workflow that integrates: in-context learning (demonstrations), explicit problem decomposition, least-to-most sequencing of sub-problems, chain-of-thought prompting (including when you would use zero-shot CoT vs a demonstrated CoT example), and an iterative self-refinement loop. Your answer must explain how these elements work together (not as independent tips), what tradeoffs you are making (e.g., context length, reliability, error propagation), and include at least two concrete prompt snippets (not full prompts) that illustrate (i) how you would elicit structured intermediate reasoning while still forcing a final answer, and (ii) how you would run critique-and-revision in self-refinement without losing the decomposed structure.

Diagnosing and Redesigning a Prompting Approach for a Decomposed Workflow

You are deploying an internal LLM assistant to help procurement analysts decide whether a proposed vendor contract requires (a) a standard review, (b) an enhanced review, or (c) an automatic rejection. The decision depends on multiple interdependent rules (e.g., data types handled, cross-border transfers, subcontractors, and exception clauses). In pilot testing, a single prompt that asks for the final decision often misses a key condition; a zero-shot “Let’s think step by step” prompt sometimes produces a long rationale but forgets to clearly state the final decision; and when you add a few demonstrations, the model becomes more consistent but still makes occasional early-step mistakes that cascade into the wrong outcome.

Design a prompting workflow (you may describe it as a sequence of LLM calls) that uses: (1) in-context learning via demonstrations, (2) explicit problem decomposition in a least-to-most progression, and (3) an iterative self-refinement loop. Your answer must explain how information flows from one step to the next, how you would prevent or detect cascading errors from early steps, and how you would ensure the model always outputs an unambiguous final decision label (a/b/c) even when using chain-of-thought style reasoning.

Stabilizing an LLM Workflow for Multi-Step Policy Compliance Decisions

You are rolling out an internal LLM assistant for Legal Ops to triage vendor contract clauses into three labels: (A) "standard/low risk", (B) "needs legal review", (C) "reject". The assistant must also produce a short justification that can be audited. In a pilot, you observe two recurring failures: (1) on complex clauses, the model gives confident but wrong labels unless it is guided through intermediate reasoning; (2) when you add a simple instruction like "Let’s think step by step," the model often produces a long rationale but sometimes forgets to output a clear final label.

You are not allowed to fine-tune the model. You can only change the prompting workflow and the content placed in the prompt. You have a strict context window budget, so you can include at most ONE worked example in the prompt, and you must keep the number of model calls per clause to no more than 3.

Case: A new clause says: "Vendor may use Customer Data to improve its services and may share Customer Data with affiliates and subcontractors for that purpose. Customer may opt out of data sharing by emailing support within 10 days of signing." Your policy requires: (i) no sharing of Customer Data with third parties for model training/service improvement unless explicitly prohibited or strongly constrained; (ii) opt-out mechanisms are considered insufficient for sensitive data; (iii) subcontractor access must be tightly limited.

Design a prompting workflow (describe the sequence of prompts/calls and what each prompt contains) that uses in-context learning, problem decomposition/least-to-most prompting, chain-of-thought (including zero-shot CoT where appropriate), and self-refinement to reduce both failure modes while staying within the constraints. Your answer must explain how the techniques interact (e.g., why you place a worked example where you do, how you decompose the decision, how you ensure a final label is always produced, and how critique/revision is used without exceeding 3 calls).

Debugging a Multi-Step LLM Workflow for Contract Clause Risk Triage

You are rolling out an internal LLM assistant for SREs to perform root-cause analysis (RCA) from incident artifacts. The assistant receives: (1) a short incident timeline, (2) 30–60 lines of logs, and (3) a list of recent deploys. The desired output is a single RCA summary with: likely cause, supporting evidence, and a recommended next action.

Constraints: You can only include ONE short demonstration in the prompt due to context limits; the assistant must work on novel incidents; and the first pilot showed two failure modes: (a) the model jumps to a plausible cause without checking evidence across artifacts, and (b) when you add “Let’s think step by step,” it sometimes produces a long analysis but forgets to state a clear final RCA.

As the prompt/workflow designer, propose a concrete prompting plan that combines: (i) in-context learning with the single demonstration, (ii) explicit problem decomposition (including a least-to-most style progression of sub-questions), (iii) chain-of-thought elicitation (including how you would use or avoid zero-shot CoT triggers), and (iv) self-refinement (critique + revision) to reduce both failure modes. Your answer must include the exact structure of the prompt(s) you would send (section headings and what each section contains) and explain why each component is placed where it is.

Designing a Robust Prompting Workflow for Multi-Step Root-Cause Analysis with Limited Examples

In least-to-most prompting, after all intermediate sub-problems have been sequentially answered, the final solution is derived by providing the language model with the original problem alongside the full context of all previously generated sub-problems and their corresponding answers. For example, to answer the original question "What was the duration of the environmental study?", the model receives the context that the study started in 2015 and ended in 2020. Using this comprehensive context, the model correctly synthesizes the final answer: the duration was 5 years.

Example of Final Problem Solving in Least-to-Most Prompting

A language model is tasked with solving the following logic puzzle: 'Sarah, David, and Emily are a doctor, a lawyer, and an engineer. The doctor is Emily's sister. David is not the lawyer.' To solve this complex problem, it is broken down into a series of simpler, sequential sub-problems. Arrange the following sub-problems in the correct logical order that builds towards the final solution.

Learn Before

Related