arXiv AI September 1, 2026 By Hehai Lin, Yu Yan, Zixuan Wang, Bo Xu, Sudong Wang, Weiquan Huang, Ruochen Zhao, Minzhi Li, Chengwei Qin

Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems

Read the original on arXiv AI →

Unified-MAS is a two-stage framework that decouples node implementation from orchestration in Automatic Multi-Agent Systems. It first searches external knowledge to synthesize domain‑specific node blueprints, then uses a perplexity‑guided reward to optimize bottleneck nodes. Experiments across four specialized domains show that adding Unified-MAS to existing baselines improves performance‑cost trade‑offs by up to 14.2% while lowering costs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 10

Inference-Time Graph Engineering for Multi-Agent LLM Workflows

arXiv:2609.05774v1 Announce Type: new Abstract: Recent multi-agent LLM systems increasingly rely on graph-structured communication to coordinate specialized agents. We revisit multi-agent orchestrati...

By Katherine Tieu, Dongqi Fu, Yinglong Xia, Hong Li, Hong Yan, Jingrui He

llms agents reinforcement-learning

arXiv AI

Oct 7

DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning

The paper introduces DHCG, a framework that dynamically constructs hierarchical collaboration graphs for large language model–based multi‑agent systems. DHCG coordinates Planner, Worker, and Generator modules to adaptively determine the composition and scale of agents during execution, guided by feedback and action‑aware preference optimization. Experiments on code generation, mathematical reasoning, and domain‑specific tasks show DHCG surpasses static and dynamic baselines, improving performance by 2.77–8.02 points and achieving a 13.06‑point gain over single‑agent baselines.

By Jie Ren, Jiakang Yuan, Chenyu Huang, Hezeer Ma, Jiayuan Fan, Tao Chen

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 12

The Illusion of Multi-Agent Advantage

arXiv:2606. 13003v1 Announce Type: new Abstract: Prevailing wisdom posits that Multi-Agent Systems (MAS) are superior to Single-Agent Systems (SAS), citing advantages like context protection, parallel processing and distributed decision-making.

By Prathyusha Jwalapuram, Hehai Lin, Chuyuan Li, Fangkai Jiao, Sudong Wang, Yifei Ming, Zixuan Ke, Chengwei Qin, Giuseppe Carenini, Shafiq Joty

agents benchmarks

arXiv AI

Jun 3

Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization

arXiv:2604. 17708v2 Announce Type: replace Abstract: Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows.

By Jiahao Huang, Peilan Xu, Xiaoya Nan, Wenjian Luo

llms agents benchmarks safety

arXiv AI

Jun 16

AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaboration

arXiv:2606. 16328v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable potential in dynamic graph reasoning, but suffer from a scaling bottleneck: current models can only handle graphs with tens of nodes, constrained by exponential reasoning overhead and finite context windows.

By Bing Hao, Ruijie Wang, Haodong Qian, Yunlong Chu, Yuhang Liu, Yumeng Lin, Minglai Shao, Jianxin Li

llms agents benchmarks

arXiv Computer Vision

Sep 1

MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming

arXiv:2410.19245v3 Announce Type: replace-cross Abstract: With the rapid advancement of Large Language Models (LLMs), LLM-based approaches have demonstrated strong problem-solving capabilities across...

By Zixiao Zhao, Jing Sun, Zhe Hou, Zhiyuan Wei, Cheng-Hao Cai, Miao Qiao, Jin Song Dong

llms agents benchmarks safety

One email a morning, machine-written

Related stories

Inference-Time Graph Engineering for Multi-Agent LLM Workflows

DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning

The Illusion of Multi-Agent Advantage

Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization

AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaboration

MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming