Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems

Shanglin Wu; Yuyang Luo; Yueqing Liang; Kaiwen Shi; Yanfang Ye; Ali Payani; Kai Shu

cs.MAMar 27, 2026

Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems

Authors: Shanglin Wu, Yuyang Luo, Yueqing Liang, Kaiwen Shi, Yanfang Ye, Ali Payani, Kai Shu

Organizations: Emory University · Illinois Institute of Technology · University of Notre Dame · Cisco Research

Abstract

Large language model (LLM) multi-agent systems can scale along two distinct dimensions: by increasing the number of agents and by improving through accumulated experience over time. Although prior work has studied these dimensions separately, their interaction under realistic cost constraints remains unclear. In this paper, we introduce a conceptual scaling view of multi-agent systems that jointly considers team size and lifelong learning ability, and we study how memory design shares this landscape. To this end, we propose LLMA-Mem, a lifelong memory framework for LLM multi-agent systems under flexible memory topologies. We evaluate LLMA-Mem on MultiAgentBench across coding, research, and database environments. Empirically, LLMA-Mem consistently improves long-horizon performance over baselines while reducing cost. Our analysis further reveals a non-monotonic scaling landscape: larger teams do not always produce better long-term performance, and smaller teams can outperform larger ones when memory better supports the reuse of experience. These findings position memory design as a practical path for scaling multi-agent systems more effectively and more efficiently over time.

Figures & tables

Figure 1: Scaling space and cost comparison of LLMA-Mem. Top: LLMA-Mem enabled scaling space for multi-agent systems. Bottom: Average token usage per task, where LLMA-Mem shows substantial cost reduction compared to baselines across models.

Figure 2: CMA curves for Claude-Sonnet-4.5 and Qwen3-next-80B, showing limited long-horizon adaptation.

Figure 3: LLMA-Mem maintains three memory components: episodic memory for task experiences, procedural memory for consolidated reusable strategies, and transactive memory for agent capabilities and team coordination. The right panel illustrates three memory topology configurations that determine how memory is distributed and accessed across agents.

Figure 4: During task execution, the system retrieves relevant memories using a relevance–importance score, updates episodic and transactive statistics after each task, and periodically consolidates episodic experiences into reusable procedural knowledge.

Model	Setting	Coding			Research			Database
Model	Setting	TS	CS	AAS	TS	CS	AAS	TS	CS	AAS
Claude-Sonnet-4.5	W.o. Memory	64.43	42.29	53.42	75.12	78.97	76.94	69.39	88.03	77.35
	MARBLE	63.05	44.71	53.99	75.17	81.84	78.37	69.70	82.96	75.70
	A-Mem	61.57	46.41	53.76	75.69	82.47	77.79	69.70	82.31	75.13
	LLMA-Mem	65.00	44.75	54.02 (+0.60)	77.62	74.11	77.77 (+0.83)	70.00	88.27	78.52 (+1.17)
Deepseek-v3.2	W.o. Memory	58.69	43.47	52.26	75.53	58.46	65.94	71.00	82.40	75.55

Table 1: Performance across environments. We report Task Score (TS), Coordination Score (CS), and Average of AS (AAS). Best results within each model and environment are boldfaced. For LLMA-Mem, the AAS cell also shows the change relative to the no-memory baseline.

Figure 5: Cumulative moving average (CMA) curves on representative settings. LLMA-Mem shows more stable long-horizon improvement than MARBLE and A-Mem, with especially margins represented by DeepSeek-v3.2 and Qwen3-32B-Instruct.

Model	Team Size	Avg TS	Avg CS	AAS	Avg Tokens
Claude-Sonnet-4.5	1	77.08	49.58	57.78	53,549
	3	76.89	48.78	58.96	139,948
	5	77.33	58.00	62.57	279,563
	7	78.22	53.11	62.21	344,323
DeepSeek-V3.2	1	72.08	48.13	49.01	41,205
	3	72.44	52.00	54.48	116,409

Table 2: Influence of team size on performance. We report average task score (TS), coordination score (CS), Average of AS (AAS), and average token usage per task.

Study	Setting	TS	CS	AAS
Topology ( $N{=}5$ )	Local	49.68	46.69	49.43
	Shared	46.79	45.96	48.62
	Hybrid	46.52	40.32	46.92
Consolidation (Local)	$N{=}2$	45.86	42.93	45.07
	$N{=}5$	49.68	46.69	49.43
	$N{=}10$	47.72	42.36	46.87

Table 3: Ablation results on the coding environment with Qwen3-32B-Instruct. The upper block compares memory topologies under a fixed consolidation interval

N{=}5

. The lower block compares consolidation intervals under the local topology.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Figure 6: An example of procedural memory piece from Qwen3-32B-Instruct on coding envrionment.

Explore similar work

Scaling Multi-Agent Intelligence with Substrate-Centric Coordination
Oct 12, 2026Zhenting Qi, Zhuokai Zhao, Rulin Shao +7Multi-Agent LLM Systems Multi-Agent Coordination
FAIR at Meta · Harvard · Meta AI +1
CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent Systems
Sep 14, 2026Chengxin Yu, Zhaoxin Fan, Faguo Wu +3Multi-Agent LLM Systems Multi-Agent Collaboration
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University · Beijing academy of blockchain and edge computing · National University of Defense Technology +1
Self-Evolving Multi-Agent Systems via Decentralized Memory
May 21, 2026Guangya Hao, Yunbo Long, Zhuokai ZhaoMulti-Agent LLM Systems LLM Agent Memory
University of Cambridge · University of Chicago

Oct 12, 2026J/K move · Enter open · S save

Scaling Multi-Agent Intelligence with Substrate-Centric Coordination

Zhenting Qi, Zhuokai Zhao, Rulin Shao, Kerem Oktar+6

FAIR at Meta · Harvard · Meta AI+1

Multi-Agent LLM Systems Multi-Agent Coordination Multi-Agent Systems Shared-Memory Multi-Agent Systems

Open paper AskPDF arXiv

Existing large language model (LLM) based multi-agent systems have been shown to scale poorly, and we identify three problems: reading burden that grows with the group, useful information diluted by shared work of unknown quality, and fragility to failed agents. We argue that the problems are largely due to agent-centric designs: the coordination structure is wired into fixed workflows, central coordinators, or peer-to-peer messaging, and recent blackboard-style methods that move the coordination into a shared medium relieve only the last problem. To close the gaps, we build ScaleMAS, where asynchronous agents interact with a shared datastore of linked messages via three operations: publishing messages with optional references to earlier ones that they build on, searching for messages by content, and visiting messages by address. Search returns at most

k

messages, so an agent's read stays bounded at any group size; results are ranked by relevance and by how often they are cited, which we find to be an effective proxy for quality; and messages persist after their producers leave, so the group carries on when individual agents fail. Across four agentic tasks, ScaleMAS outperforms agent-centric and blackboard-style baselines at lower inference compute, continues to scale up to 128 agents, and tolerates losing agents midway.

Abstract

Explore similar work

Scaling Multi-Agent Intelligence with Substrate-Centric Coordination

CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent Systems

Self-Evolving Multi-Agent Systems via Decentralized Memory