# Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning

arXiv: https://arxiv.org/abs/2608.03138 · HTML: https://mlsanity.com/paper/2608.03138/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 63 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents](https://mlsanity.com/paper/2410.13185/) (2024)
- [LitLLM: A Toolkit for Scientific Literature Review](https://mlsanity.com/paper/2402.01788/) (2024)
- [SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing](https://mlsanity.com/paper/2503.04629/) (2025)
- [Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents](https://mlsanity.com/paper/2510.14967/) (2025)
- [SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding](https://mlsanity.com/paper/2408.15545/) (2024)
- [A Vision for Auto Research with LLM Agents](https://mlsanity.com/paper/2504.18765/) (2025)
- [AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research](https://mlsanity.com/paper/2507.13300/) (2025)
- [Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning](https://mlsanity.com/paper/2507.01551/) (2025)
- [SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods](https://mlsanity.com/paper/2507.21463/) (2025)
- [SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More](https://mlsanity.com/paper/2601.05688/) (2026)
- [Towards AI-Assisted Research Writing: Benchmarking LLMs for AI/ML Introduction Generation](https://mlsanity.com/paper/2508.14273/) (2025)
- [Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokens](https://mlsanity.com/paper/2601.09728/) (2025)

## Abstract (arXiv)

Generating a rigorous paper introduction with large language models (LLMs) remains challenging, since it requires coordinating background, gap identification, method and contribution within a coherent narrative. Existing solutions externalize this process as multi-stage prompts or agent workflows which are expensive and vulnerable to cross-stage drift. We propose StructPO, a struct-aware policy learning framework that internalizes the entire multi-stage writing workflow into a single-pass policy controlled by explicit stage tokens. StructPO introduces struct-aware credit assignment to decouple local stage quality from global coherence and refinement-guided optimization to internalize revision behavior into the first-pass policy. Experiments show that StructPO improves semantic alignment, structural rationality and inference efficiency over workflow-based baselines, generalizes to out-of-domain settings, and remains competitive with GPT-5.1 in human evaluation when scaled to Qwen3-32B. These results show that internalizing academic writing workflows through fine-grained policy optimization offers a viable alternative to costly external orchestration.