paper-with-me

Papers

Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems

2025-07-22 · Chengxuan Xia, Qianye Wu, Sixuan Tian, Yilun Hao arxiv

Large language model (LLM) agents have shown increasing promise for collaborative task completion. However, existing multi-agent frameworks often rely on static workflows, fixed roles, and limited inter-agent communication, reducing their effectiveness in open-ended, high-complexity domains. This paper proposes a coordination framework that enables adaptiveness through three core mechanisms: dynamic task routing, bidirectional feedback, and parallel agent evaluation. The framework allows agents to reallocate tasks based on confidence and workload, exchange structured critiques to iteratively improve outputs, and crucially compete on high-ambiguity subtasks with evaluator-driven selection of the most suitable result. We instantiate these principles in a modular architecture and demonstrate substantial improvements in factual coverage, coherence, and efficiency over static and partially adaptive baselines. Our findings highlight the benefits of incorporating both adaptiveness and structured competition in multi-agent LLM systems.

📄 PDF Abstract BibTeX arXiv:2507.17061

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models

2024-02-23 · Jongyoon Song, Nohil Park, Bongkyu Hwang, Jaewoong Yun 외

Abstractive summarization models often generate factually inconsistent content particularly when the parametric knowledge of the model conflicts with the knowledge in the input document. In this paper, we analyze the rob…

Abstractive Text SummarizationContrastive LearningcounterfactualData Augmentation

HyPar-Flow: Exploiting MPI and Keras for Scalable Hybrid-Parallel DNN Training using TensorFlow

2019-11-12 · Ammar Ahmad Awan, Arpan Jain, Quentin Anthony, Hari Subramoni 외

To reduce training time of large-scale DNNs, scientists have started to explore parallelization strategies like data-parallelism, model-parallelism, and hybrid-parallelism. While data-parallelism has been extensively stu…

Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts

2025-03-07 · Weigao Sun, Disen Lan, Tong Zhu, Xiaoye Qu 외

Linear Sequence Modeling (LSM) like linear attention, state space models and linear RNNs, and Mixture-of-Experts (MoE) have recently emerged as significant architectural improvements. In this paper, we introduce Linear-M…

Mixture-of-ExpertsState Space Models

Pre-training Meets Clustering: A Hybrid Extractive Multi-document Summarization Model

2023-05-25 · International Conference on Hybrid Intelligent Systems 2023 5 · Akanksha Karotia, Seba Susan

In this era where a large amount of information has flooded the Internet, manual extraction and consumption of relevant information is very difficult and time-consuming. Therefore, an automated document summarization too…

ClusteringDocument Summarizationdocument understandingExtractive Text Summarization+4

Tesseract: Parallelize the Tensor Parallelism Efficiently

2021-05-30 · Boxiang Wang, Qifan Xu, Zhengda Bian, Yang You

Together with the improvements in state-of-the-art accuracies of various tasks, deep learning models are getting significantly larger. However, it is extremely difficult to implement these large models because limited GP…

GPULanguage Modelling