scriptoriumadmin/ReMe
1
0
Fork 0
mirror of https://github.com/agentscope-ai/ReMe.git synced 2026-10-24 05:47:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

docs: fix compaction benchmark links with verified permalinks

Browse source
This commit is contained in:
jinli.yl 2026-10-16 11:12:26 +08:00
parent cf55876810
commit 4cb8f2fd53
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/en/context_compaction.md
View file

@ -120,7 +120,7 @@ latency and total cost alongside token reduction. ReMe does not automatically su
## Span-selection experiment
The [benchmark protocol and results (Chinese)](https://github.com/agentscope-ai/ReMe/blob/main/benchmark/compaction/RESULTS.md)
The [benchmark protocol and results (Chinese)](https://github.com/jinliyl/ReMe/blob/cf5587681070735db6b49fe90f93c752a17935eb/benchmark/compaction/RESULTS.md)
describe a local run on October 15, 2026, using a synthetic Hermes payment trajectory and a controlled long-log
augmentation. It compares full evidence, Jev span selection, head/tail clipping and ordinary Qwen summaries under
600/1000 evidence-token allowances, with identical system/user instructions and evaluation prompts.

2
docs/zh/context_compaction.md
View file

@ -111,7 +111,7 @@ ReMe 不会自动生成摘要或写入长期记忆。
## 分块压缩实验
[Benchmark 评测方案与结果](https://github.com/agentscope-ai/ReMe/blob/main/benchmark/compaction/RESULTS.md)
[Benchmark 评测方案与结果](https://github.com/jinliyl/ReMe/blob/cf5587681070735db6b49fe90f93c752a17935eb/benchmark/compaction/RESULTS.md)
记录了 2026-10-15 的本地对照实验：以 Hermes 采集的合成支付 trajectory 及其长日志增噪变体，比较完整证据、
Jev 分块筛选、首尾截取和普通 Qwen 摘要。证据预算为 600 / 1000 token，所有组保持相同的 system、user 和评测提示。
分块排序只在实验脚本中实现；上述 `compact_context` 的配对判断与低概率预览策略保持不变。