Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models
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 AugmentationHyPar-Flow: Exploiting MPI and Keras for Scalable Hybrid-Parallel DNN Training using TensorFlow
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
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 ModelsPre-training Meets Clustering: A Hybrid Extractive Multi-document Summarization Model
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+4Tesseract: Parallelize the Tensor Parallelism Efficiently
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