Jia Li, Chen Zhang, Yan Zhou, Yuhan Li, Kaichi Yu, Miao Peng, Zhongjian Zhang, Yuyao Wang, Mo Chi, Bing Tong
We lifted 4 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| DSAIL-Memory/EvoMemBench | canonical | 4 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| deprecated | Ran | DSAIL-Memory/EvoMemBench/EvoMemBench-Memory-Systems/MemOS/src/memos/deprecation.py pointer only (licence: NONE) · get_code("ab3353e27ad3508a") |
| deprecated_class | Ran | DSAIL-Memory/EvoMemBench/EvoMemBench-Memory-Systems/MemOS/src/memos/deprecation.py pointer only (licence: NONE) · get_code("744138a7b8a9d7ad") |
| deprecated_parameter | Ran | DSAIL-Memory/EvoMemBench/EvoMemBench-Memory-Systems/MemOS/src/memos/deprecation.py pointer only (licence: NONE) · get_code("ee8ecb22d0b43e1b") |
| require_python_package | Ran | DSAIL-Memory/EvoMemBench/EvoMemBench-Memory-Systems/MemOS/src/memos/dependency.py pointer only (licence: NONE) · get_code("034999cf0be2894e") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability remains under-evaluated, largely because existing benchmarks do not provide a systematic way to assess memory mechanisms. In this paper, we study agent memory from a self-evolving perspective and introduce EvoMemBench, a unified benchmark organized along two axes: memory scope (in-episode vs. cross-episode) and memory content (knowledge-oriented vs. execution-oriented). We compare 15 representative memory methods with strong long-context baselines under a standardized protocol. Results show that current memory systems are still far from a general solution: long-context baselines remain highly competitive, memory helps most when the current context is insufficient or tasks are difficult, and no single memory form works consistently across all settings. Retrieval-based methods remain strong for knowledge-intensive settings, whereas procedural and long-term memory methods are more effective for execution-oriented tasks when their stored experience matches the task structure. We hope EvoMemBench facilitates future research on more effective memory systems for LLM-based agents. Our code is available at https://github.com/DSAIL-Memory/EvoMemBench.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2605.18421")
get_code_for_paper("2605.18421")
have("2605.18421")
Connect an agent — have() is free.