Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models

• URL: http://arxiv.org/abs/2503.08275v2
• Date: Tue, 25 Mar 2025 18:27:55 GMT
• Title: Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models
• Authors: Ruibin Xiong, Yimeng Chen, Dmitrii Khizbullin, Mingchen Zhuge, Jürgen Schmidhuber,
• Abstract summary: Long-form writing agents require flexible integration and interaction across information retrieval, reasoning, and composition.<n>Current approaches rely on predetermined and rigid thinking patterns to generate outlines before writing.<n>We propose a general agent framework that achieves human-like adaptive writing.
• Score: 26.79639857578783
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-form writing agents require flexible integration and interaction across information retrieval, reasoning, and composition. Current approaches rely on predetermined workflows and rigid thinking patterns to generate outlines before writing, resulting in constrained adaptability during writing. In this paper we propose a general agent framework that achieves human-like adaptive writing through recursive task decomposition and dynamic integration of three fundamental task types, i.e. retrieval, reasoning, and composition. Our methodology features: 1) a planning mechanism that interleaves recursive task decomposition and execution, eliminating artificial restrictions on writing workflow; and 2) integration of task types that facilitates heterogeneous task decomposition. Evaluations on both fiction writing and technical report generation show that our method consistently outperforms state-of-the-art approaches across all automatic evaluation metrics, which demonstrate the effectiveness and broad applicability of our proposed framework.

Related papers

• Explanatory Summarization with Discourse-Driven Planning [58.449423507036414]
  We present a plan-based approach that leverages discourse frameworks to organize summary generation and guide explanatory sentences. Specifically, we propose two discourse-driven planning strategies, where the plan is conditioned as part of the input or part of the output prefix. Empirical experiments on three lay summarization datasets show that our approach outperforms existing state-of-the-art methods in terms of summary quality.
  arXiv  Detail & Related papers  (2025-04-27T19:47:36Z)
• Learning Task Representations from In-Context Learning [73.72066284711462]
  Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning.<n>We introduce an automated formulation for encoding task information in ICL prompts as a function of attention heads.<n>We show that our method's effectiveness stems from aligning the distribution of the last hidden state with that of an optimally performing in-context-learned model.
  arXiv  Detail & Related papers  (2025-02-08T00:16:44Z)
• DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization [2.8201999897313015]
  Abstractive summarization has made significant strides in condensing and rephrasing large volumes of text into coherent summaries.<n>Existing models often struggle to adapt to the intricate structure and specialized content of such documents.<n>We introduce DocSum, a domain-adaptive abstractive summarization framework tailored for administrative documents.
  arXiv  Detail & Related papers  (2024-12-11T08:36:50Z)
• EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration [63.112790050749695]
  We introduce EAGER, a novel generative recommendation framework that seamlessly integrates both behavioral and semantic information. We validate the effectiveness of EAGER on four public benchmarks, demonstrating its superior performance compared to existing methods.
  arXiv  Detail & Related papers  (2024-06-20T06:21:56Z)
• Dynamic Embeddings with Task-Oriented prompting [0.8287206589886881]
  The structure of DETOT is detailed, highlighting its task-specific adaptation, continuous feedback loop, and mechanisms for preventing overfitting. Empirical evaluations demonstrate its superiority over existing methods.
  arXiv  Detail & Related papers  (2024-05-17T23:18:15Z)
• Interactive Editing for Text Summarization [30.46273082913698]
  REVISE is a framework designed to facilitate iterative editing and refinement of draft summaries by human writers. At its core, REVISE incorporates a modified fill-in-the-middle model with the encoder-decoder architecture.
  arXiv  Detail & Related papers  (2023-06-05T17:43:53Z)
• Improving Task Generalization via Unified Schema Prompt [87.31158568180514]
  Unified Prompt is a flexible and prompting method, which automatically customizes the learnable prompts for each task according to the task input schema. It models the shared knowledge between tasks, while keeping the characteristics of different task schema. The framework achieves strong zero-shot and few-shot performance on 16 unseen tasks downstream from 8 task types.
  arXiv  Detail & Related papers  (2022-08-05T15:26:36Z)
• TAGPRIME: A Unified Framework for Relational Structure Extraction [71.88926365652034]
  TAGPRIME is a sequence tagging model that appends priming words about the information of the given condition to the input text. With the self-attention mechanism in pre-trained language models, the priming words make the output contextualized representations contain more information about the given condition. Extensive experiments and analyses on three different tasks that cover ten datasets across five different languages demonstrate the generality and effectiveness of TAGPRIME.
  arXiv  Detail & Related papers  (2022-05-25T08:57:46Z)
• Automated Concatenation of Embeddings for Structured Prediction [75.44925576268052]
  We propose Automated Concatenation of Embeddings (ACE) to automate the process of finding better concatenations of embeddings for structured prediction tasks. We follow strategies in reinforcement learning to optimize the parameters of the controller and compute the reward based on the accuracy of a task model.
  arXiv  Detail & Related papers  (2020-10-10T14:03:20Z)
• Incomplete Utterance Rewriting as Semantic Segmentation [57.13577518412252]
  We present a novel and extensive approach, which formulates it as a semantic segmentation task. Instead of generating from scratch, such a formulation introduces edit operations and shapes the problem as prediction of a word-level edit matrix. Our approach is four times faster than the standard approach in inference.
  arXiv  Detail & Related papers  (2020-09-28T09:29:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.