Multi-Agent Transactive Memory

Abstract:Decentralized deployment of LLM agents with diverse capabilities motivates infrastructure for knowledge sharing across heterogeneous agent populations. Just as search engines index human-generated artifacts for human problem solving, retrieval systems can organize agent-generated artifacts for reuse across agents, extending retrieval-augmented generation from human-authored documents to agent-generated ones. Agent trajectories in particular encode reusable procedural knowledge, yet are typically discarded after a single use or retained only by the producing agent, forcing newly instantiated agents to rediscover existing solutions. We propose Multi-Agent Transactive Memory (MATM), a framework for population-level storage and retrieval of agent trajectories, where producer agents contribute trajectories to a shared repository and consumer agents retrieve them to improve task execution. In interactive environments with long, procedurally rich trajectories (ALFWorld and WebArena), retrieving from MATM improves downstream task performance and reduces interaction steps without coordination or joint training, positioning MATM as a design pattern for population-level experience sharing in open agent ecosystems.

Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR)

arXiv:2606.19911 [cs.AI]

(or arXiv:2606.19911v2 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.19911 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.