AI RESEARCH
AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents
arXiv CS.CV
•
ArXi:2603.18429v1 Announce Type: new Long-horizon GUI agents are a key step toward real-world deployment, yet effective interaction memory under prevailing paradigms remains under-explored. Replaying full interaction sequences is redundant and amplifies noise, while summaries often erase dependency-critical information and traceability. We present AndroTMem, a diagnostic framework for anchored memory in long-horizon Android GUI agents. Its core benchmark, AndroTMem-Bench, comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65.