AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents
- URL: http://arxiv.org/abs/2603.18429v1
- Date: Thu, 19 Mar 2026 02:45:21 GMT
- Title: AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents
- Abstract summary: We present AndroTMem, a diagnostic framework for anchored memory in long-horizon Android GUI agents.<n>Our benchmark, AndroTMem-Bench, comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65)<n>We propose Anchored State Memory (ASM), which represents interaction sequences as a compact set of causally linked intermediate-state anchors.
- Score: 35.5648433882265
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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). We evaluate agents with TCR (Task Complete Rate), focusing on tasks whose completion requires carrying forward critical intermediate state; AndroTMem-Bench is designed to enforce strong step-to-step causal dependencies, making sparse yet essential intermediate states decisive for downstream actions and centering interaction memory in evaluation. Across open- and closed-source GUI agents, we observe a consistent pattern: as interaction sequences grow longer, performance drops are driven mainly by within-task memory failures, not isolated perception errors or local action mistakes. Guided by this diagnosis, we propose Anchored State Memory (ASM), which represents interaction sequences as a compact set of causally linked intermediate-state anchors to enable subgoal-targeted retrieval and attribution-aware decision making. Across multiple settings and 12 evaluated GUI agents, ASM consistently outperforms full-sequence replay and summary-based baselines, improving TCR by 5%-30.16% and AMS by 4.93%-24.66%, indicating that anchored, structured memory effectively mitigates the interaction-memory bottleneck in long-horizon GUI tasks. The code, benchmark, and related resources are publicly available at [https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem).
Related papers
- A Task-State Representation for Long-Horizon Mobile GUI Agents [53.359524744953575]
Task-State Representation (TSR) is a training-free framework that explicitly decouples task state from sensory input.<n> Experiments across four mobile GUI benchmarks validate TSR's effectiveness, yielding up to a 12 absolute point increase in success rate.
arXiv Detail & Related papers (2026-07-01T06:37:21Z) - eMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agents [1.8047694351309203]
We present eMEM, a hybrid graph-based memory system for embodied agents operating in physical environments.<n>eMEM fills this gap with a multi-index architecture (ITE for structured storage, hlib for approximate nearest neighbour semantic search, and an R-tree for spatial queries)<n>We also introduce eMEM-Bench v1, a benchmark we construct over ProcTHOR-10K scenes for embodied memory evaluation.
arXiv Detail & Related papers (2026-06-02T09:22:12Z) - MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems [69.06764269022925]
We study how current memory-augmented agents perform in realistic, interference-heavy, long-horizon settings.<n> MINTEval is a benchmark featuring long, highly interconnected contexts with frequently updated information.<n>Overall, MINTEval has 15.6k question-answering pairs over long-horizon contexts averaging 138.8k tokens and extending to 1.8M tokens per instance.
arXiv Detail & Related papers (2026-05-18T15:43:35Z) - AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
arXiv Detail & Related papers (2026-03-17T13:22:54Z) - AMA: Adaptive Memory via Multi-Agent Collaboration [54.490349689939166]
We propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities.<n>AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods.
arXiv Detail & Related papers (2026-01-28T08:09:49Z) - Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents [20.357475946040054]
We introduce textscMem2ActBench, a benchmark for evaluating whether agents can proactively leverage long-term memory to execute tool-based actions.<n>A reverse-generation method produces 400 tool-use tasks, with human evaluation confirming 91.3% are strongly memory-dependent.
arXiv Detail & Related papers (2026-01-13T06:22:32Z) - MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments [6.12783571098263]
MEMTRACK is a benchmark designed to evaluate long-term memory and state tracking in multi-platform agent environments.<n>Each benchmark instance provides a chronologically platform-interleaved timeline, with noisy, conflicting, cross-referring information.<n>Our benchmark tests memory capabilities such as acquistion, selection and conflict resolution.
arXiv Detail & Related papers (2025-10-01T18:34:03Z) - MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents [84.62985963113245]
We introduce MEM1, an end-to-end reinforcement learning framework that enables agents to operate with constant memory across long multi-turn tasks.<n>At each turn, MEM1 updates a compact shared internal state that jointly supports memory consolidation and reasoning.<n>We show that MEM1-7B improves performance by 3.5x while reducing memory usage by 3.7x compared to Qwen2.5-14B-Instruct on a 16-objective multi-hop QA task.
arXiv Detail & Related papers (2025-06-18T19:44:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.