Search papers, labs, and topics across Lattice.
This paper introduces LLMA-Mem, a lifelong memory framework for LLM multi-agent systems, and evaluates its performance on MultiAgentBench across coding, research, and database environments. The study investigates the interaction between team size and lifelong learning ability under realistic cost constraints, revealing a non-monotonic scaling landscape where larger teams don't always guarantee better long-term performance. Empirically, LLMA-Mem improves long-horizon performance and reduces cost, demonstrating the importance of memory design for efficient scaling.
Forget scaling team size alone – smarter memory design lets smaller LLM agent teams beat larger ones in long-term performance.
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 \textbf{LLMA-Mem}, a lifelong memory framework for LLM multi-agent systems under flexible memory topologies. We evaluate LLMA-Mem on \textsc{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.
