Metraipolis › archive › dc_d8f341b9575b
Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning — arXiv:2608.03138
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03138
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:18:36.316Z
- SHA-256 of the archived text
26120b54c50da55dd587493ac728f48e5c1f62e9d1b3a7f705221bd5fefdd231- Stable URL of this page
https://metraipolis.com/documento/dc_d8f341b9575b
How to cite
Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning — arXiv:2608.03138 — arXiv (en), https://arxiv.org/abs/2608.03138 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8f341b9575b (Metraipolis archive dc_d8f341b9575b, sha256 26120b54c50da55dd587493ac728f48e5c1f62e9d1b3a7f705221bd5fefdd231)
BibTeX
@misc{dcd8f341b9575b,
title = {Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning — arXiv:2608.03138},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03138},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8f341b9575b; sha256 26120b54c50da55dd587493ac728f48e5c1f62e9d1b3a7f705221bd5fefdd231},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03138. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.03138 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T12:05:53.005Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).