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.

From the source
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
huggingface.co

Visit source ↗huggingface.co

Announced: 11 Aug 2026 13:37 UTC
Detected: 14 Aug 2026 13:13 UTC (+2d after)

Other stories

Hugging Face · 28 AugThe Open ASR Leaderboard Adds Its First Global South LanguageCapability change

Google Research · 27 AugPlanetary prediction engine: Automating global models via Earth AIResearch paper

OpenAI · 27 AugBetter answers, broader thinking: What students gain from ChatGPT and critical-thinking trainingResearch paper

LG AI Research · 27 Aug

[ACL 2026] ReSQL: A Self-Improving Text-to-SQL Framework through Retrieval-Augmented Error Reasoning

Research paper

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot in Visual Studio — August update