paper-with-me

홈 › Papers

Learning Task Decomposition to Assist Humans in Competitive Programming

2024-06-07 · Jiaxin Wen, Ruiqi Zhong, Pei Ke, Zhihong Shao, Hongning Wang, Minlie Huang

When using language models (LMs) to solve complex problems, humans might struggle to understand the LM-generated solutions and repair the flawed ones. To assist humans in repairing them, we propose to automatically decompose complex solutions into multiple simpler pieces that correspond to specific subtasks. We introduce a novel objective for learning task decomposition, termed assistive value (AssistV), which measures the feasibility and speed for humans to repair the decomposed solution. We collect a dataset of human repair experiences on different decomposed solutions. Utilizing the collected data as in-context examples, we then learn to critique, refine, and rank decomposed solutions to improve AssistV. We validate our method under competitive programming problems: under 177 hours of human study, our method enables non-experts to solve 33.3\% more problems, speeds them up by 3.3x, and empowers them to match unassisted experts.

📄 PDF Abstract BibTeX arXiv:2406.04604

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Learning a Hierarchical Planner from Humans in Multiple Generations

2023-10-17 · Leonardo Hernandez Cano, Yewen Pu, Robert D. Hawkins, Josh Tenenbaum 외

A typical way in which a machine acquires knowledge from humans is by programming. Compared to learning from demonstrations or experiences, programmatic learning allows the machine to acquire a novel skill as soon as the…

Design and Evaluation of an Assisted Programming Interface for Behavior Trees in Robotics

2026-02-10 · Jonathan Styrud, Matteo Iovino, Rebecca Stower, Mart Kartašev 외 arxiv

The possibility to create reactive robot programs faster without the need for extensively trained programmers is becoming increasingly important. So far, it has not been explored how various techniques for creating Behav…

A Showdown of ChatGPT vs DeepSeek in Solving Programming Tasks

2025-03-16 · Ronas Shakya, Farhad Vadiee, Mohammad Khalil

The advancement of large language models (LLMs) has created a competitive landscape for AI-assisted programming tools. This study evaluates two leading models: ChatGPT 03-mini and DeepSeek-R1 on their ability to solve co…

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

2026-04-03 · DeepReinforce Team, Xiaoya Li, Xiaofei Sun, Guoyin Wang 외 arxiv

Competitive programming remains one of the last few human strongholds in coding against AI. The best AI system to date still underperforms the best humans competitive programming: the most recent best result, Google's Ge…

Reinforcement Learning

A global constraint for the capacitated single-item lot-sizing problem

2019-07-04 · Grigori German, Hadrien Cambazard, Jean-Philippe Gayon, Bernard Penz

The goal of this paper is to set a constraint programming framework to solve lot-sizing problems. More specifically, we consider a single-item lot-sizing problem with time-varying lower and upper bounds for production an…