paper-with-me

Papers

Programming Puzzles

2021-06-10 · Tal Schuster, Ashwin Kalyan, Oleksandr Polozov, Adam Tauman Kalai

We introduce a new type of programming challenge called programming puzzles, as an objective and comprehensive evaluation of program synthesis, and release an open-source dataset of Python Programming Puzzles (P3). Each puzzle is defined by a short Python program $f$, and the goal is to find an input which makes $f$ return True. The puzzles are objective in that each one is specified entirely by the source code of its verifier $f$, so evaluating $f$ is all that is needed to test a candidate solution. They do not require an answer key or input/output examples, nor do they depend on natural language understanding. The dataset is comprehensive in that it spans problems of a range of difficulties and domains, ranging from trivial string manipulation problems, to classic programming puzzles (e.g., Tower of Hanoi), to interview/competitive-programming problems (e.g., dynamic programming), to longstanding open problems in algorithms and mathematics (e.g., factoring). We develop baseline enumerative program synthesis, GPT-3 and Codex solvers that are capable of solving puzzles -- even without access to any reference solutions -- by learning from their own past solutions. Codex performs best, solving up to 18% of 397 test problems with a single try and 80% of the problems with 1,000 tries per problem. In a small user study, we find a positive correlation between puzzle-solving performance and coding experience, and between the puzzle difficulty for humans and AI solvers. Therefore, further improvements on P3 could have a significant impact on many program synthesis areas.

📄 PDF Abstract BibTeX arXiv:2106.05784

Code (3)

microsoft/PythonProgrammingPuzzles 공식 구현
google-research/babelcode
suzgunmirac/meta-prompting

Tasks

Code GenerationNatural Language UnderstandingProgram Synthesis

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Weight Decay 설명 없음
Multi-Head Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음

Similar Papers 제목 키워드 기반

ADAPTIVE GENERATION OF PROGRAMMING PUZZLES

2019-09-25 · Ashwin Kalyan, Oleksandr Polozov, Adam Tauman Kalai

AI today is far from being able to write complex programs. What type of problems would be best for computers to learn to program, and how should such problems be generated? To answer the first question, we suggest progra…

Program Synthesis

Heuristics, Answer Set Programming and Markov Decision Process for Solving a Set of Spatial Puzzles

2019-02-16 · Thiago Freitas dos Santos, Paulo E. Santos, Leonardo A. Ferreira, Reinaldo A. C. Bianchi 외

Spatial puzzles composed of rigid objects, flexible strings and holes offer interesting domains for reasoning about spatial entities that are common in the human daily-life's activities. The goal of this work is to inves…

Q-LearningReinforcement LearningReinforcement Learning (RL)

Ludii and XCSP: Playing and Solving Logic Puzzles

2019-06-29 · Cédric Piette, Éric Piette, Matthew Stephenson, Dennis J. N. J. Soemers 외

Many of the famous single-player games, commonly called puzzles, can be shown to be NP-Complete. Indeed, this class of complexity contains hundreds of puzzles, since people particularly appreciate completing an intractab…

Solving Temporal Puzzles

2016-06-01 · CVPR 2016 6 · Caglayan Dicle, Burak Yilmaz, Octavia Camps, Mario Sznaier

Many physical phenomena, within short time windows, can be explained by low order differential relations. In a discrete world, these relations can be described using low order difference equations or equivalently low ord…

Time SeriesTime Series Analysis

Logic-of-Thought: Empowering Large Language Models with Logic Programs for Solving Puzzles in Natural Language

2025-05-22 · Naiqi Li, Peiyuan Liu, Zheng Liu, Tao Dai 외

Solving puzzles in natural language poses a long-standing challenge in AI. While large language models (LLMs) have recently shown impressive capabilities in a variety of tasks, they continue to struggle with complex puzz…

Natural Language Understanding