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

Abstract

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.