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
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
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
arXiv:2607. 11126v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools served by shared providers and accessed by heterogeneous downstream agents.
By Yue Fang, Zhibang Yang, Fangkai Yang, Xiaoting Qin, Liqun Li, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
By Yuyao Wang, Zhongjian Zhang, Mo Chi, Kaichi Yu, Yuhan Li, Miao Peng, Bing Tong, Chen Zhang, Yan Zhou, Jia Li
MemoryArena is a new evaluation gym that benchmarks agent memory in interdependent multi‑session tasks. Unlike prior benchmarks that test memorization or single‑session action in isolation, MemoryArena requires agents to acquire memory while interacting with the environment and then use that memory to guide future decisions across a range of tasks such as web navigation, planning, information search, and formal reasoning. The benchmark reveals that agents excelling on existing long‑context memory tests perform poorly here, highlighting a gap in current memory evaluation methods.
By Zexue He, Yu Wang, Churan Zhi, Yuanzhe Hu, Tzu-Ping Chen, Lang Yin, Ze Chen, Tong Arthur Wu, Siru Ouyang, Zihan Wang, Jiaxin Pei, Julian McAuley, Yejin Choi, Alex Pentland
arXiv:2608. 04830v1 Announce Type: new Abstract: Memory is essential as language agents move from isolated tasks to long-horizon, stateful workflows, yet existing evaluations often reduce it to retrieval or question answering.
By Bo Wang, Yuqian Yao, Enxi Wang, Luozhijie Jin, Yang Liu, Yiran Suo, Yuxuan Cai, Enyu Zhou, Yufei Gao, Honglin Guo, Tianyu Huai, Li Ji, Zhikai Lei, Bufan Li, Lizhi Lin, Jinxiu Liu, Jie Yang, Jiazheng Zhou, Maosen Zhou, Pengfang Qian, Shichun Liu, Guanshan Liu, Hao Zheng, Yunhao Yu, Hang Yan, Jihua Kang, Xinchi Chen, Xipeng Qiu
arXiv:2607. 20495v1 Announce Type: new Abstract: Multi-agent systems decompose complex tasks into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for caching intermediate results across queries.
By Anas Mohamed, Kaizan Haque, Azal Ahmad Khan, Chetan Sharma, Shuwen Ge, Ali Anwar