The paper introduces TOCOMAS, a Topology‑Coherent Multi‑Agent System that enforces topological coherence—consistent responsibility, handoff, and memory boundaries—within self‑evolving multi‑agent systems. TOCOMAS grounds task graphs in tool interfaces, groups compatible task nodes into reusable responsibility domains, and derives collaboration and memory visibility rules that respect task dependencies. In experiments on BBEH, WorkBench, SWE‑Bench‑Verified, and CoMemBench, TOCOMAS outperforms baseline methods in task success, verified progress, handoffs, and memory isolation.
By Sen Zhao, Ruiqi Kong, Zuyu Zhang, Lifeng Shen, Xinyu He, Xu Zhang, Qinghua Zhang
arXiv:2607. 09493v1 Announce Type: new Abstract: Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive.
By Sanjana Pedada, Aditya Dhavala, Neelraj Patil
MemCo introduces a memory‑centric collaboration framework that equips large language model agents with both local and global memory spaces. Local memory preserves environment‑specific details, while global memory captures transferable workflows from local trajectories. During online interaction, MemCo selectively routes relevant memories based on the agent’s state and decision phase, enabling reuse of other agents’ experiences without over‑generalizing environment‑specific information.
By Xinting Liao, Siyan Liu, Rabab K. Ward, Holger R. Roth, Xiaoxiao Li
arXiv:2606.00756v2 Announce Type: replace
Abstract: LLM-based Web agents are increasingly deployed on edge servers to carry out long-horizon tasks on behalf of users with low latency. However, the li...
By Yannan Wang, Longli Yang, Zhen Liu, Abhishek Kumar, Carsten Maple
WorkflowOps is a multi‑agent workflow orchestration framework that learns collaboration priors from historical workflows. It uses a transition probability matrix to guide DAG construction, a sufficiency‑driven loop to create new agents on demand via an LLM, and a layered semantic matching strategy to reduce LLM calls. Experiments show that WorkflowOps improves end‑to‑end pass rates, especially on structured, decomposable tasks.
By Qi Cheng, Shengyu Chen, Wei Cheng, Zhengzhang Chen, Xiaowei Jia, Haoyu Wang, Haifeng Chen
MASBench is a benchmark for evaluating large language model (LLM)-based multi‑agent systems (MAS) under partial observability, a realistic constraint where agents only see limited environmental information. The benchmark is structured into three progressive task categories—Reasoning, Scheduling, and Game—and assesses three collaboration mechanisms: Protocol, Memory, and Routing. It provides deterministic evaluation metrics such as performance score, communication cost, and cost effectiveness, and includes empirical results across various LLM backbones to guide effective MAS design.
By Qizhi Chu, Zekai Yu, Sijie Wen, Yang Liu, Chen Qian, Cheng Yang, Chuan Shi, Zhiyuan Liu
arXiv:2607. 22578v1 Announce Type: new Abstract: The proliferation of Large Language Models (LLMs) has shifted serving systems from processing isolated requests to orchestrating high-concurrency, multi-tenant agentic workflows.
By Size Li, Zhiqing Tang, Hongrui Liang, Jianxiong Guo, Jiong Lou, Tian Wang, Weijia Jia
arXiv:2611.01728v1 Announce Type: cross
Abstract: Large language model (LLM)-based multi-agent systems (MAS) tackle challenging tasks by dividing work among agents and coordinating their contribution...
By Zerui Chen, Qinggang Zhang, Qichuan Liu, Zhishang Xiang, Zhimin Wei, Yunbo Tang, Zhuo Li, Jinsong Su, Zhihong Zhang
UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
By Pengyu Zhu, Lijun Li, Yaxing Lyu, Qianxin Luo, Jingyi Yang, Yi Liu, Tingfeng Hui, Xinyu Yuan, Li Sun, Sen Su, Jing Shao
arXiv:2606. 06448v1 Announce Type: new Abstract: LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories.
By Yasmine Omri, Ziyu Gan, Zachary Broveak, Robin Geens, Zexue He, Alex Pentland, Marian Verhelst, Tsachy Weissman, Thierry Tambe
arXiv:2606. 00756v1 Announce Type: new Abstract: Deploying lightweight Large Language Model (LLM) agents on edge servers can reduce latency and move agentic services closer to users, but resource-constrained edge models often struggle with long-horizon tasks that require persistent memory, subgoal tracking, and reflection.
By Yannan Wang, Longli Yang, Zhen Liu, Abhishek Kumar, Carsten Maple
arXiv:2606. 24535v1 Announce Type: new Abstract: Multi-agent LLM environments require robust mechanisms for shared knowledge management.
By Yanki Margalit, Nurit Cohen-Inger, Erni Avram, Ran Taig, Oded Margalit