Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911441641013248 |
|---|---|
| author | Xia, Chengxuan Wu, Qianye Tian, Sixuan Hao, Yilun |
| author_facet | Xia, Chengxuan Wu, Qianye Tian, Sixuan Hao, Yilun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17061 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems Xia, Chengxuan Wu, Qianye Tian, Sixuan Hao, Yilun Multiagent Systems Artificial Intelligence Information Retrieval 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. |
| title | Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems |
| topic | Multiagent Systems Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2507.17061 |