Surrogate-Guided Memory Retrieval for Autonomous Agents
Published in Manuscript in preparation, 2026
Role: co-first author · Status: in progress.
We study memory retrieval for autonomous agents — deciding which past experiences an agent should recall to act well now. Instead of relying on raw semantic similarity, we train the retriever offline with a learned surrogate that scores how much a candidate memory improves downstream task success. Supervised by Ye Yuan and Prof. Xue (Steve) Liu at Mila – Quebec AI Institute.
Recommended citation: Yonghan Yang*, Ye Yuan*, et al. Surrogate-Guided Memory Retrieval for Autonomous Agents. Manuscript in preparation, 2026. (* equal contribution)