AI · Official
Microsoft's TokenEconomizer Cuts AI Coding Agent Costs by Learning From Past Work
Microsoft Research blog ·

At a glance
Microsoft Research and its partners built TokenEconomizer, an open-source plugin that helps AI coding agents use fewer tokens. It learns from past sessions in the same code repository, so agents waste less effort on repeated work.
Key points
- The plugin reads each finished session's log and updates what it knows about the repository.
- It uses three methods: short notes for repeated knowledge, removing tools the agent is unlikely to use, and stepping in when an agent keeps failing the same way.
- In tests on 277 SWE-Bench tasks across six repositories, it cut average cost by 18.4% to 30.9% with five agent and model combinations.
- The tool works without changing the agent or its underlying model, and savings grow as it gathers more experience.
Why it matters
AI coding agents charge for every token they use, so lowering token use can reduce costs for developers without changing the model.
Original source
TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient
Microsoft Research blog · Nov 17, 02:01 KST
Read on Microsoft Research blog ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to Microsoft Research blog.
More from this field
- Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST - Walter Writes AI Tool Rewrites AI Text to Sound More Human, Ad Test Shows
This short video is a sponsored ad for Walter Writes AI, a tool that rewrites AI-generated text so it reads more like a person wrote it. The creator says they ran a paragraph through its detector, rewrote the flagged parts, and compared the scores before and after.
TheAIGRID · Nov 21, 06:15 KST - Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST