The full skill instructions and embedded helper script are in skills/pdf2plot.md at the root of this repository. Read that file now and follow its instructions.
other
2026-06-12-evoarena-memory-evolution-llm-agents
ANo problem foundyingwang/paper-reads
这篇在领域里的位置。 大模型智能体的评测这几年走过了一条从"答题"到"做事"的路：WebArena 考网页操作，SWE-bench 考改代码，GAIA 考带工具的综合任务。但这些基准有一个共同的隐含假设，即环境是一张冻结的快照，任务做完一次便是终点。与之相对地，真实部署里的智能体面对的是同一个环境的持续演化：接口在改版，依赖在升级，代码库在长出新的里程碑，用户的偏好也在悄悄换边。另一条相关的线是智能体的记忆系统，Mem0、A-Mem 这一类工作让智能体把经验沉淀下来，但沉淀的方式几乎都是"合并到最新状态"。这篇论文同时站在这两条线的缺口上：评测一侧造了一个专门考"环境演化"的基准 EvoArena，方法一侧提出把记忆当版本库来管的 EvoMem。
2026-06-12-evoarena-memory-evolution-llm-agents got grade A on our automated scan on 2026-10-23.
Before you install
- Read any scripts this skill ships.
- Note every URL it fetches.
- Check allowed-tools and hooks.
Embed this grade
Add this badge to your README. It shows the current grade from CheckSkills.
Report this skill if the grade looks wrong, or if something slipped through.
Related
Run all code generation (protobuf, sqlc, frontend build)
name: ship description: Release protocol: pre-flight checks, changelog, semantic version, tag, deploy. disable-model-invocation: true
name: init description: Bootstrap the .resonance/ project memory (soul, state, docs scaffold). Run once per new project. disable-model-invocation: true
name: goal description: The autonomous goal loop: frame, decompose, then build and verify each slice against real checks, bounded, never auto-ship. disable-model-invocation: true