Towards Robust Long-Lived Agents: Benchmarking Experience Lifecycles in Evolving Environments

The paper introduces ReScopeBench, a benchmark designed to evaluate how agents manage the lifecycle of experience in evolving environments. It differentiates between structural experience—knowledge about how an environment is organized—and rule experience—principles that guide decisions across tasks. Using an experience-first construction approach, the study tracks how agents acquire, reuse, and revise experience across task streams, revealing that while retained experience boosts performance, agents often fail to keep it current when environments change.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• benchmarks