AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

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

Junchuan Yu, Yuyang Sun

AAAI 2026 · Multi-agent systems and games › LLM agents · approach: Agent data synthesis and behavior studies · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes WRitEer, a multi-objective, preference-driven multi-agent framework that generates more human-like advanced text through iterative multi-dimensional feedback rather than single-turn LLM generation.

Problem

Current LLM-based text generation is mostly single-turn and lacks the interactivity and multi-dimensional feedback of human writing, so outputs fall short in naturalness and emotional expressiveness.

Approach

A multi-agent writing framework that optimizes multiple objectives guided by preferences and multi-dimensional feedback, mimicking the iterative drafting-and-revision process of human writers.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DPO fine-tuning of the Writer (ablation)WRitEer-Qwen2.5-7B · CNN/DailyMailaverage score: 7.67 -> 8.39Improved
add DPO fine-tuning of the Writer (ablation)WRitEer-Qwen2.5-7B · CNN/DailyMailLR&P: 6.48 -> 8.12Improved
add Reader-Editor-Writer framework instead of direct answerQwen2.5-7B · CNN/DailyMailaverage score: 4.97 -> 8.39Improved
use WRitEer framework versus multi-turn conversation on same Grok-style baselinemulti-turn conversation · CNN/DailyMailaverage score: 7.13 -> 7.67Improved
scale Writer backbone from Qwen2.5-7B to Qwen3-235B in WRitEerWRitEer · CNN/DailyMailaverage score: 7.67 -> 8.81Improved
add multi-turn conversation to Qwen2.5-7B-DPOQwen2.5-7B-DPO · CNN/DailyMailaverage score: 4.97 (std 0.94)Mixed
use larger or newer direct-answer LLMDirect Answer LLMs · CNN/DailyMailaverage score: 4.47 to 4.77No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy