Learning to Share: Selective Memory for Efficient Parallel Agentic Systems

TL;DR

This paper introduces Learning to Share (LTS), a learned shared-memory mechanism that enables selective information sharing among parallel agents, significantly reducing computational costs while maintaining or improving task performance.

Contribution

LTS provides a novel learned shared-memory system with a controller trained via reinforcement learning to efficiently reuse information across parallel agent teams.

Findings

LTS reduces runtime significantly compared to memory-free baselines.

LTS maintains or improves task performance on benchmarks.

LTS effectively identifies globally useful information for sharing.

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-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/