MemGround: Long-Term Memory Evaluation Kit for Large Language Models in Gamified Scenarios
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908967315177472 |
|---|---|
| author | Ding, Yihang Xia, Wanke Zhao, Yiting Su, Jinbo Yang, Jialiang Zhang, Zhengbo Wang, Ke Yang, Wenming |
| author_facet | Ding, Yihang Xia, Wanke Zhao, Yiting Su, Jinbo Yang, Jialiang Zhang, Zhengbo Wang, Ke Yang, Wenming |
| contents | Current evaluations of long-term memory in LLMs are fundamentally static. By fixating on simple retrieval and short-context inference, they neglect the multifaceted nature of complex memory systems, such as dynamic state tracking and hierarchical reasoning in continuous interactions. To overcome these limitations, we propose MemGround, a rigorous long-term memory benchmark natively grounded in rich, gamified interactive scenarios. To systematically assess these capabilities, MemGround introduces a three-tier hierarchical framework that evaluates Surface State Memory, Temporal Associative Memory, and Reasoning-Based Memory through specialized interactive tasks. Furthermore, to comprehensively quantify both memory utilization and behavioral trajectories, we propose a multi-dimensional metric suite comprising Question-Answer Score (QA Overall), Memory Fragments Unlocked (MFU), Memory Fragments with Correct Order (MFCO), and Exploration Trajectory Diagrams (ETD). Extensive experiments reveal that state-of-the-art LLMs and memory agents still struggle with sustained dynamic tracking, temporal event association, and complex reasoning derived from long-term accumulated evidence in interactive environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14158 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MemGround: Long-Term Memory Evaluation Kit for Large Language Models in Gamified Scenarios Ding, Yihang Xia, Wanke Zhao, Yiting Su, Jinbo Yang, Jialiang Zhang, Zhengbo Wang, Ke Yang, Wenming Computation and Language Artificial Intelligence Current evaluations of long-term memory in LLMs are fundamentally static. By fixating on simple retrieval and short-context inference, they neglect the multifaceted nature of complex memory systems, such as dynamic state tracking and hierarchical reasoning in continuous interactions. To overcome these limitations, we propose MemGround, a rigorous long-term memory benchmark natively grounded in rich, gamified interactive scenarios. To systematically assess these capabilities, MemGround introduces a three-tier hierarchical framework that evaluates Surface State Memory, Temporal Associative Memory, and Reasoning-Based Memory through specialized interactive tasks. Furthermore, to comprehensively quantify both memory utilization and behavioral trajectories, we propose a multi-dimensional metric suite comprising Question-Answer Score (QA Overall), Memory Fragments Unlocked (MFU), Memory Fragments with Correct Order (MFCO), and Exploration Trajectory Diagrams (ETD). Extensive experiments reveal that state-of-the-art LLMs and memory agents still struggle with sustained dynamic tracking, temporal event association, and complex reasoning derived from long-term accumulated evidence in interactive environments. |
| title | MemGround: Long-Term Memory Evaluation Kit for Large Language Models in Gamified Scenarios |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.14158 |