Topological Coherence for Self-evolving Multi-agent Systems

Sen Zhao; Ruiqi Kong; Zuyu Zhang; Lifeng Shen; Xinyu He; Xu Zhang; Qinghua Zhang

cs.AISep 29, 2026

Topological Coherence for Self-evolving Multi-agent Systems

Authors: Sen Zhao, Ruiqi Kong, Zuyu Zhang, Lifeng Shen, Xinyu He, Xu Zhang, Qinghua Zhang

Organizations: Academy of Advanced Interdisciplinary Studies, Chongqing University of Posts and Telecommunications, Chongqing, China · School of Artificial Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, China · Towngas, China · School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China

Abstract

Complex tasks inherently couple workflow structure, agent responsibility, collaboration, and memory access: task regions delimit responsibility and tool scope, cross-region dependencies give rise to handoffs, and ownership boundaries delimit private and selectively shared memory. Existing methods can jointly optimize agent and communication structures, yet such optimization does not by itself require responsibility, handoff, and memory boundaries to remain consistent with task dependencies. We term this requirement topological coherence. We introduce TOCOMAS, a Topology-Coherent Multi-Agent System. TOCOMAS grounds a task graph in tool interfaces, organizes compatible task nodes into reusable responsibility domains, and derives dependency-induced and profile-conditioned collaboration together with boundary-regulated memory visibility. During online self-evolution, TOCOMAS proposes coupled changes to agent, collaboration, and memory policies, retaining for subsequent tasks only candidates that satisfy structural constraints and improve evaluated reward. Across BBEH, WorkBench, SWE-Bench-Verified, and CoMemBench, TOCOMAS improves task success over baselines across backbones. CoMemBench also shows gains over the self-evolving baseline in verified progress, handoffs, and memory isolation.

Figures & tables

Figure 1: Topological coherence in ToCoMAS. Task topology jointly induces agent responsibilities, collaboration interfaces, and memory boundaries, which evolve as a coupled organization.

Figure 2: Overview of ToCoMAS . Task-derived responsibility regions organize agents, handoffs, and memory boundaries; online evolution preserves their coherence.

Backbone	Organization	Method	General Task Performance			CoMemBench
Backbone	Organization	Method	BBEH $\uparrow$	WorkBench $\uparrow$	SWE-V $\uparrow$	SR $\uparrow$	VNCR $\uparrow$	VHS $\uparrow$	ICS $\uparrow$
Qwen3.8-27B	Control	Direct LLM Call	19.13	19.28	9.80	0.00	8.81	34.50	0.00
	Prespecified	Peer Review	46.52	37.10	30.50	1.00	30.74	33.37	19.10
	Prespecified	SMoA	37.17	37.25	35.00	4.00	38.73	43.32	10.10
	Automatically designed	ADAS	32.61	62.17	34.20	0.00	13.91	27.73	7.40
	Automatically designed	OMAC	41.09	55.94	39.50	2.00	32.98	40.51	17.30

Table 1: Overall comparison on BBEH, WorkBench, SWE-Bench-Verified, and CoMemBench.

Variant	WorkBench	CoMemBench
Variant	SR $\uparrow$	SR $\uparrow$	VNCR $\uparrow$	VHS $\uparrow$	ICS $\uparrow$
w/o Topological Agent Organization	69.86	4.00	27.27	37.97	67.14
w/o Structure-Adaptive Collaborative Orchestration	67.25	0.00	28.20	10.15	66.70
w/o Boundary-Preserving Memory Coordination	68.55	6.50	36.30	42.07	64.94
w/o Coherence-Constrained Structural Evolution	71.16	10.60	40.07	47.80	80.80
ToCoMAS	77.68	14.30	41.60	51.00	84.90

Table 2: Architectural ablations and fixed-versus-evolving comparison of ToCoMAS .

Explore similar work

CoMemBench: Benchmarking Collaborative Memory Boundaries across Multi-Agent Workflow Topologies
Sep 26, 2026Sen Zhao, Ruiqi Kong, Zuyu Zhang +5Multi-Agent Workflows Multi-Agent Coordination
Academy of Advanced Interdisciplinary Studies, Chongqing University of Posts and Telecommunications, Chongqing, China · School of Artificial Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, China · Towngas, China +2
TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems
May 10, 2026Chen Xu, Yicheng Hu, Ruizi Wang +4Multi-Agent Evolution Co-Evolution
1Carnegie Mellon University · University of Science and Technology of China · 3National University of Singapore +1
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
Jul 30, 2026Mao-xun Huang, Jerry Wang, Yi-Cheng Lai +3Model-Based Multi-Agent Systems Topology
Department of Computer Science, Cornell University, United States · Department of Computer Science, University of Illinois Urbana-Champaign, United States · Institute of Information Science, Academia Sinica, Taiwan

Sep 26, 2026, cs.AIJ/K move · Enter open · S save

CoMemBench: Benchmarking Collaborative Memory Boundaries across Multi-Agent Workflow Topologies

Sen Zhao, Ruiqi Kong, Zuyu Zhang, Lifeng Shen+4

Academy of Advanced Interdisciplinary Studies, Chongqing University of Posts and Telecommunications, Chongqing, China · School of Artificial Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, China · Towngas, China+2

Multi-Agent Workflows Multi-Agent Coordination Distributed Optimization Topology

Open paper AskPDF arXiv

Multi-agent workflows require task-relevant information to be shared across agents, while irrelevant, stale, unverified, or incompatible information must remain isolated. We call this task-conditioned scope of information a collaborative memory boundary. Workflow topology determines which intermediate artifacts are applicable to which downstream workers and when they cease to be valid, thereby providing a structural stress dimension for sharing and isolation. Existing memory benchmarks primarily evaluate retention and retrieval, whereas multi-agent benchmarks emphasize coordination and end-to-end completion, leaving topology-conditioned memory boundaries largely unmeasured. We introduce CoMemBench, an execution-grounded benchmark for collaborative memory sharing and isolation across multi-agent workflow topologies. It constructs 800 composite workflows across four domains from source-grounded dependency graphs, with node-local specifications, verifiable artifact handoffs, native evaluators, and matched isolation challenges. CoMemBench measures workflow completion, verified node progress, required-handoff reliability, isolation robustness, and token cost. Experiments reveal a sharing-isolation trade-off: broader context improves information availability but can weaken isolation, while system rankings shift across topologies and artifact violations.

Abstract

Explore similar work

CoMemBench: Benchmarking Collaborative Memory Boundaries across Multi-Agent Workflow Topologies

TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems

MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems