# Hugging Face — Thinking of ACE? We Can Do It with Fewer Tokens

- Company: Hugging Face (huggingface.co)
- Announced: 2026-08-11T13:37:10+00:00
- Category: research-paper
- Subject: Platform
- Models affected: DeepSeek-V3.2, gpt-oss-120b
- Source: https://huggingface.co/blog/ibm-research/altk-evolve-sldd
- Record: https://forck.live/items/3744-thinking-of-ace-we-can-do-it-with-fewer-tokens

IBM Research introduces ALTK-Evolve, an agentic memory system that learns from agent trajectories and delivers guidelines selectively, achieving better accuracy and lower token cost compared to ACE on AppWorld benchmarks with DeepSeek-V3.2 and gpt-oss-120b models.

## Evidence

Verbatim from https://huggingface.co/blog/ibm-research/altk-evolve-sldd:

> On AppWorld, with the same base ReAct agent, running both systems in-house: Model TGC / SGC Tokens/task DeepSeek-V3.2 ACE 80.4 / 73.2 634K ALTK-Evolve 89.3 / 80.4 263K gpt-oss-120b ACE 54.8 / 35.7 777K ALTK-Evolve 56.0 / 37.5 116K

---

Record: https://forck.live/items/3744-thinking-of-ace-we-can-do-it-with-fewer-tokens
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md