# LLM×MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources

arXiv: https://arxiv.org/abs/2504.05732 · HTML: https://mlsanity.com/paper/2504.05732/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Hurdles to Progress in Long-form Question Answering](https://mlsanity.com/paper/2103.06332/) (2021)
- [PaSa: An LLM Agent for Comprehensive Academic Paper Search](https://mlsanity.com/paper/2501.10120/) (2025)
- [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://mlsanity.com/paper/2408.15232/) (2024)
- [OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking](https://mlsanity.com/paper/2501.09751/) (2025)
- [LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models](https://mlsanity.com/paper/2410.09342/) (2024)
- [Taxonomy Tree Generation from Citation Graph](https://mlsanity.com/paper/2410.03761/) (2024)
- [SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section](https://mlsanity.com/paper/2408.16444/) (2024)

## Built on by (most cited first, 2 of 2)

- [SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation](https://mlsanity.com/paper/2506.12689/) (2025)
- [DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability](https://mlsanity.com/paper/2605.29522/) (2026)

## Abstract (arXiv)

Long-form generation is crucial for a wide range of practical applications, typically categorized into short-to-long and long-to-long generation. While short-to-long generations have received considerable attention, generating long texts from extremely long resources remains relatively underexplored. The primary challenge in long-to-long generation lies in effectively integrating and analyzing relevant information from extensive inputs, which remains difficult for current large language models (LLMs). In this paper, we propose LLM×MapReduce-V2, a novel test-time scaling strategy designed to enhance the ability of LLMs to process extremely long inputs. Drawing inspiration from convolutional neural networks, which iteratively integrate local features into higher-level global representations, LLM×MapReduce-V2 utilizes stacked convolutional scaling layers to progressively expand the understanding of input materials. Both quantitative and qualitative experimental results demonstrate that our approach substantially enhances the ability of LLMs to process long inputs and generate coherent, informative long-form articles, outperforming several representative baselines. Both LLM×MapReduce-V2 and SurveyEval are publicly available at https://github.com/thunlp/LLMxMapReduce .