让并行智能体共享记忆，减少重复计算，提升效率。
Learning to Share: Selective Memory for Efficient Parallel Agentic Systems
- 引入全局记忆库与轻量控制器，选择性共享跨团队中间结果。
- 在AssistantBench和GAIA上运行时间显著降低，性能不降反升。
- 适合需要高效并行推理的复杂任务系统，如多智能体协作场景。
智能体系统通过协调多个智能体迭代推理、调用工具并交换中间结果来解决复杂任务。为提升鲁棒性和解题质量，近期方法采用多个并行运行的智能体团队探索多样化的推理路径。然而，平行执行带来显著计算开销：不同团队在处理相似子问题或执行类似步骤时，会重复进行大量重叠计算。为此，本文提出学习共享（LTS），一种用于并行智能体框架的可学习共享记忆机制，支持选择性跨团队信息复用，同时控制上下文增长。LTS引入所有团队均可访问的全局记忆库，以及一个轻量级控制器，决定中间智能体步骤是否存入记忆。控制器通过分步强化学习与使用感知的信用分配进行训练，能够识别在并行执行中具有全局价值的信息。在AssistantBench和GAIA基准上的实验表明，相较于无记忆的并行基线，LTS显著降低总体运行时间，同时保持或提升任务性能，证明了可学习的记忆准入策略是提升并行智能体系统效率的有效途径。
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。