EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents

ACL ARR 2026 January Submission3032 Authors

Keywords: episodic memory, multimodal memory, interactive evaluation, LLM agents, vision-language agents, trajectory-grounded QA

Abstract: We introduce EMemBench, a programmatic benchmark for evaluating long-term memory of agents through interactive games. Rather than using a fixed set of questions, EMemBench generates questions from each agent’s own trajectory, covering both text and visual game environments. Each template computes verifiable ground truth from underlying game signals, with controlled answerability and balanced coverage over memory skills: single/multi-hop recall, induction, temporal, spatial, logical, and adversarial. We evaluate memory agents with strong LMs/VLMs as backbones, using in-context prompting as baselines. Across 15 text games and multiple visual seeds, results are far from saturated: induction and spatial reasoning are persistent bottlenecks, especially in visual setting. Persistent memory yields clear gains for open backbones on text games, but improvements are less consistent for VLM agents, suggesting that visually grounded episodic memory remains an open challenge. A human study further confirms the difficulty of EMemBench.

Paper Type: Long

Research Area: Resources and Evaluation

Research Area Keywords: AI / LLM Agents, Resources and Evaluation, Multimodality and Language Grounding to Vision, Robotics and Beyond, Question Answering

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English

Submission Number: 3032