cover

Conducting a Qualitative Analysis by Comparing the Outputs of Our Think-and-Execute Framework

25 Mar 2025

We conduct a qualitative analysis by comparing the outputs of our approach (THINKAND-EXECUTE) with those of the baseline methods.

cover

Generated Pseudocode Prompts During Our Think-And-Execute Experiment

22 Mar 2025

Some examples of generated pseudocode prompts during our experiments.

cover

Generated Analyses: Dyck Languages, Geometric Shapes, and More

22 Mar 2025

Generated analysis of dyck languages, geometric shapes, reasoning about colored objects, and more.

cover

Examples of Human-Written Pseudocode Prompts

22 Mar 2025

Here are some examples of Human-Written pseudocode prompts

cover

The Prompts We Used in Our Experiments

22 Mar 2025

Check out the prompts we used during our think-and-execute experiments.

cover

Details of Think-and-Execute That You Don't Want to Miss

21 Mar 2025

We highlight some components of code prompt that would be helpful in describing the underlying reasoning logic.

cover

Think-and-Execute: The Experimental Details

21 Mar 2025

We use several LLMs, including GPT-3.5-Turbo and GPT-4, which are available via OpenAI API[4], and open-source LLM, CodeLlama

cover

Think-and-Execute: The Takeaway

21 Mar 2025

In this paper, we present THINK-AND-EXECUTE, an algorithmic reasoning framework that generates a logic for solving the given task into a pseudocode

cover

Think-and-Execute: The Limitations That We Face

21 Mar 2025

A possible limitation of our approach is that we focus on algorithmic reasoning, as we believe it is the best setting to assess LLMs’ capabilities