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-aware credit assignment, allowing it to identify information that is globally useful across parallel executions. Experiments on the AssistantBench and GAIA benchmarks show that LTS significantly reduces overall runtime while matching or improving task performance compared to memory-free parallel baselines, demonstrating that learned memory admission is an effective strategy for improving the efficiency of parallel agentic systems. Project page: https://joefioresi718.github.io/LTS_webpage/

翻译：智能体系统通过协调多个能迭代推理、调用工具并交换中间结果的智能体来解决复杂任务。为提升鲁棒性和解决方案质量，近期方法部署多个并行运行的智能体团队以探索多样化推理轨迹。然而，并行执行会带来显著计算开销：当不同团队独立推理相似子问题或执行类似步骤时，会反复进行大量重叠计算。针对这些局限，本文提出"学会共享 (LTS)"机制，这是一种用于并行智能体框架的可学习共享记忆机制，能在控制上下文膨胀的同时实现跨团队选择性信息复用。LTS引入全局记忆库（所有团队均可访问）和轻量级控制器，该控制器决定是否将中间智能体步骤写入记忆。控制器通过基于步骤的强化学习与使用感知信用分配进行训练，使其能够识别跨并行执行具有全局价值的信息。在AssistantBench和GAIA基准上的实验表明：与无记忆的并行基线相比，LTS在显著降低总运行时间的同时，任务性能保持匹配或有所提升，验证了可学习记忆准入机制是提升并行智能体系统效率的有效策略。项目页面：https://joefioresi718.github.io/LTS_webpage/