Thinking of ACE? We Can Do It with Fewer Tokens

Thinking of ACE? We Can Do It with Fewer Tokens We Can Do It with Fewer Tokens Enterprise Article Published August 11, 2026 Upvote 33 Vatche Isahagian Vatche ibm-research Jayaram Radhakrishnan jayaramkr ibm-research Vinod Muthusamy vinodmut ibm-research Gaodan Fang gaodan-fang ibm-research Punleuk Oum illeatmyhat ibm-research G Thomas gsthomasx ibm-research Ashwath Vaithinathan Aravindan ashwath-vaithina ibm-research Evelyn Duesterwald evduester ibm-research Merve Unuvar mrvnvr ibm-research ALTK-Evolve and ACE both let an agent learn from its own trajectories. The difference is what they do with what they learn — and that decides the token bill.

This ProductUpdate is relevant to the technology intelligence record because it involves DeepSeek, gpt-oss, GPT. The source article should remain the factual reference for follow-up coverage.

• We Can Do It with Fewer Tokens Enterprise Article Published August 11, 2026 Upvote 33 Vatche Isahagian Vatche ibm-research Jayaram Radhakrishnan jayaramkr ibm-research Vinod Muthusamy vinodmut ibm-research Gaodan Fang gaodan-fang ibm-research Punleuk Oum illeatmyhat ibm-research G Thomas gsthomasx ibm-research Ashwath Vaithinathan Aravindan ashwath-vaithina ibm-research Evelyn Duesterwald evduester ibm-research Merve Unuvar mrvnvr ibm-research ALTK-Evolve and ACE both let an agent learn from its own trajectories.
• The difference is what they do with what they learn — and that decides the token bill.
• Give an LLM agent a realistic multi-step task — split a bill, find a song, reconcile an order across nine simulated apps — and when it fails, it usually isn't for lack of knowledge.
• It mis-paginates an API, resolves the wrong person, or returns a value when none was asked for.
• The model knows the APIs; what it hasn't internalized is how to use them reliably .
• That's learnable from the agent's own history.