# Learning Task Decomposition to Assist Humans in Competitive Programming

arXiv: https://arxiv.org/abs/2406.04604 · HTML: https://mlsanity.com/paper/2406.04604/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Recursively Summarizing Books with Human Feedback](https://mlsanity.com/paper/2109.10862/) (2021)
- [Supervising strong learners by amplifying weak experts](https://mlsanity.com/paper/1810.08575/) (2018)
- [Successive Prompting for Decomposing Complex Questions](https://mlsanity.com/paper/2212.04092/) (2022)
- [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://mlsanity.com/paper/2208.11640/) (2022)
- [Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions](https://mlsanity.com/paper/2212.10561/) (2022)
- [Humans decompose tasks by trading off utility and computational cost](https://mlsanity.com/paper/2211.03890/) (2022)
- [Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions](https://mlsanity.com/paper/2210.10860/) (2022)

## Built on by (most cited first, 14 of 14)

- [Language Models Learn to Mislead Humans via RLHF](https://mlsanity.com/paper/2409.12822/) (2024)
- [Prover-Verifier Games improve legibility of LLM outputs](https://mlsanity.com/paper/2407.13692/) (2024)
- [Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs](https://mlsanity.com/paper/2502.19411/) (2025)
- [From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging](https://mlsanity.com/paper/2410.01215/) (2024)
- [The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment](https://mlsanity.com/paper/2412.16468/) (2024)
- [Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling](https://mlsanity.com/paper/2412.15305/) (2024)
- [Unsupervised Elicitation of Language Models](https://mlsanity.com/paper/2506.10139/) (2025)
- [A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users](https://mlsanity.com/paper/2509.18632/) (2025)
- [AdaptBot: Combining LLM with Knowledge Graphs and Human Input for Generic-to-Specific Task Decomposition and Knowledge Refinement](https://mlsanity.com/paper/2502.02067/) (2025)
- [The Superalignment of Superhuman Intelligence with Large Language Models](https://mlsanity.com/paper/2412.11145/) (2024)
- [MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation](https://mlsanity.com/paper/2604.08782/) (2026)
- [Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization](https://mlsanity.com/paper/2503.07660/) (2025)
- [Superalignment with Dynamic Human Values](https://mlsanity.com/paper/2503.13621/) (2025)
- [Towards Neuro-symbolic Causal Rule Synthesis, Verification, and Evaluation Grounded in Legal and Safety Principles](https://mlsanity.com/paper/2604.28087/) (2026)

## Abstract (arXiv)

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.