Agents that accumulate experience across tasks often get worse instead of better because they remember irrelevant actions. This paper introduces AdMem, a system that stores only helpful procedures by checking each action's outcome against its expected result before saving it. Each stored memory has a utility value that determines whether it should be kept, merged, or forgotten. Across 707 tasks in eight domains, AdMem solved 441 tasks, significantly outperforming both a memoryless agent (388 tasks) and a workflow-induction baseline (312 tasks). This matters because it shows that selective memory, not just more memory, makes agents more reliable.
AI agents can perform worse when they keep unmanaged memories
Across 707 tasks, the authors’ managed memory system outperformed a memoryless agent, while a baseline that stored reusable workflows performed worse in seven of eight domains.
Big Tech
Runzhe Wang · Huilin Lu · Shengjie Liu · Li Dong · Zhihuai Zhu
Princeton University · Amazon · Arm
Research Digest··2 min read

In one line
AdMem improves long-horizon task-solving by storing only procedurally useful actions, using per-action credit assignment and a utility-driven memory lifecycle.
Before you read this
Three ideas this paper builds onagent memoryA repository where an agent stores past interactions and outcomes to inform future decisions.241 papers →credit assignmentDetermining which actions or steps in a sequence contributed to a final outcome, often for reinforcement learning.190 papers →continual learningA learning paradigm where a model sequentially acquires knowledge from multiple tasks without significantly forgetting earlier ones.72 papers →
Read it as
Wang and colleagues report that remembering past work does not automatically help AI agents: poorly managed memories can reduce task completion.
The authors evaluated agents across eight domains in AgentBoard, comparing AdMem with a memoryless ReAct agent and a baseline that extracts reusable workflows from experience.
How it works
stage by stageThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.