EUVIMEDEUVIMED entdecken
Crossref

WRitEer: A Multi-Objective, Preference-Driven Multi-Agent Framework for Human-Like Advanced Text Generation

Junchuan Yu, Yuyang Sun

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29856-29864

DOI: 10.1609/aaai.v40i35.40232 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Junchuan Yu und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advanced text generation is paramount for enhancing the naturalness of human-computer interaction and improving emotional expressiveness. Current mainstream methods largely rely on large language models (LLMs) for single-turn generation, often lacking the interactivity and multi-dimensional feedback mechanisms inherent in human writing. This limitation frequently results in generated texts that fall short in terms of depth, fluency, and stylistic sophistication. To address these deficiencies, this paper proposes WRitEer (Writer-Reader iterative tuning with Editor-Driven evolution and refinement), an interactive multi-agent collaborative human-like writing framework. Centered around an LLM, this framework integrates multi-objective optimization with preference fine-tuning techniques. It introduces three synergistic agents: the Reader, responsible for discourse analysis and indicator generation; the Editor, which constructs prompts based on feedback indicators and iteratively refines them through an evolutionary search; and the Writer, which generates text based on these refined prompts and continuously self-optimizes via a DPO mechanism that incorporates preference feedback. Experimental results consistently demonstrate that this ``generate-evaluate-reflect-optimize'' workflow significantly outperforms single LLM models across multiple datasets, yielding advanced rich texts that exhibit superior human-like style, coherence, expressiveness, and controllability.

Zitieren

APA

Yu, J., & Sun, Y. (2026). WRitEer: A Multi-Objective, Preference-Driven Multi-Agent Framework for Human-Like Advanced Text Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29856-29864. https://doi.org/10.1609/aaai.v40i35.40232

Vancouver

Yu J, Sun Y. WRitEer: A Multi-Objective, Preference-Driven Multi-Agent Framework for Human-Like Advanced Text Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29856-29864. doi:10.1609/aaai.v40i35.40232

BibTeX
@article{Yu2026,
  author = {Yu, Junchuan and Sun, Yuyang},
  title = {WRitEer: A Multi-Objective, Preference-Driven Multi-Agent Framework for Human-Like Advanced Text Generation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {35},
  pages = {29856--29864},
  doi = {10.1609/aaai.v40i35.40232}
}
Kostenlos starten →