More Memory, Worse Agents: Error Reproduction and Anti-Persistence Memory Design in LLM Agents

The paper proposes Anti-Persistence, a memory design that accumulates trajectories and outcomes, reconstructs task guidance on demand, and discards it after execution, so that errors in stored abstractions are not repeatedly reused. The authors call the phenomenon in which errors are regenerated through a cycle of abstraction, execution, and re-abstraction error reproduction. Across multiple benchmarks and backbone models, Anti-Persistence achieves higher held-out task success rates and the lowest average LLM call cost among the evaluated memory designs.