Learning To Share: Selective Memory For Efficient Parallel Agentic Systems

Abstract

Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results. To improve robustness and solution quality, recent approaches deploy multiple agent teams running in parallel to explore diverse reasoning trajectories. However, parallel execution comes at a significant computational cost: when different teams independently reason about similar sub-problems or execute analogous steps, they repeatedly perform substantial overlapping computation. To address these limitations, in this paper, we propose Learning to Share (LTS), a learned shared-memory mechanism for parallel agentic frameworks that enables selective cross-team information reuse while controlling context growth. LTS introduces a global memory bank accessible to all teams and a lightweight controller that decides whether intermediate agent steps should be added to memory or not. The controller is trained using stepwise reinforcement learning with usage

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfioresi2026learning

Related papers

• Selectively Sharing Experiences Improves Multi-agent Reinforcement Learning (2023)4.61
• Learning To Share In Multi-agent Reinforcement Learning (2021)0.00
• Multi-task Multi-agent Shared Layers Are Universal Cognition Of Multi-agent Coordination (2023)0.00
• Cautiously-optimistic Knowledge Sharing For Cooperative Multi-agent Reinforcement Learning (2023)5.84
• Experience Sharing Between Cooperative Reinforcement Learning Agents (2019)0.00
• Improving Coordination In Small-scale Multi-agent Deep Reinforcement Learning Through Memory-driven Communication (2019)12.25
• Reducing Redundant Computation In Multi-agent Coordination Through Locally Centralized Execution (2024)0.00
• Scaling Multi-agent Reinforcement Learning With Selective Parameter Sharing (2021)0.00