Hugging Face Blog·· 2026-08-11
Thinking of ACE? We Can Do It with Fewer Tokens
Thinking of ACE? We Can Do It with Fewer Tokens
AI summary
Hugging Face's ALTK-Evolve and ACE both provide agent memory without weight updates, but differ in delivery: ACE injects the full playbook at every step, while ALTK-Evolve retrieves a small number of strongly supported guidelines for each task.
Selection record
Threshold 60Official, first-handFirst 38Second 42
Not admittedSum of both 80 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：讨论LLM Agent记忆与推理优化技术
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co