paper-with-me

Papers

SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation

2025-06-15 · Xiaofeng Shi, Qian Kou, Yuduo Li, Ning Tang, Jinxin Xie, Longbin Yu, Songjing Wang, Hua Zhou

The rapid growth of scientific literature demands robust tools for automated survey-generation. However, current large language model (LLM)-based methods often lack in-depth analysis, structural coherence, and reliable citations. To address these limitations, we introduce SciSage, a multi-agent framework employing a reflect-when-you-write paradigm. SciSage features a hierarchical Reflector agent that critically evaluates drafts at outline, section, and document levels, collaborating with specialized agents for query interpretation, content retrieval, and refinement. We also release SurveyScope, a rigorously curated benchmark of 46 high-impact papers (2020-2025) across 11 computer science domains, with strict recency and citation-based quality controls. Evaluations demonstrate that SciSage outperforms state-of-the-art baselines (LLM x MapReduce-V2, AutoSurvey), achieving +1.73 points in document coherence and +32% in citation F1 scores. Human evaluations reveal mixed outcomes (3 wins vs. 7 losses against human-written surveys), but highlight SciSage's strengths in topical breadth and retrieval efficiency. Overall, SciSage offers a promising foundation for research-assistive writing tools.

📄 PDF Abstract BibTeX arXiv:2506.12689

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelRetrieval

Similar Papers 제목 키워드 기반

CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation

2024-12-15 · Zhendong Mi, Renming Zheng, Haowen Zhong, Yue Sun 외

Recent advances in agentic LLMs have demonstrated great capabilities in Verilog code generation. However, existing approaches either use LLM-assisted single-agent prompting or cooperation-only multi-agent learning, which…

Code GenerationPrompt Learning

LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback

2025-06-02 · Thai Hoang, Kung-Hsiang Huang, Shirley Kokane, JianGuo Zhang 외

Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and re…

Large Language Model

M$^2$-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data Mining

2026-02-05 · Rui Lv, Juncheng Mo, Tianyi Chu, Chen Rao 외 arxiv

Graphical User Interface (GUI) agent is pivotal to advancing intelligent human-computer interaction paradigms. Constructing powerful GUI agents necessitates the large-scale annotation of high-quality user-behavior trajec…

What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices

2024-09-03 · Zhi Chen, Qiguang Chen, Libo Qin, Qipeng Guo 외

Recent advancements in large language models (LLMs) with extended context windows have significantly improved tasks such as information extraction, question answering, and complex planning scenarios. In order to achieve …

Question AnsweringQuestion GenerationQuestion-Generation

Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning

2024-11-21 · Hang Zhou, Yehui Tang, Haochen Qin, Yujie Yang 외

The efficacy of large language models (LLMs) on downstream tasks usually hinges on instruction tuning, which relies critically on the quality of training data. Unfortunately, collecting high-quality and diverse data is b…