AI News

Trending story

Microsoft Research and others release open-source plugin TokenEconomizer

1 reports1 story updatesUpdated Nov 17 01:01

Understand this story

AI overview

On November 17, 2026, UC Berkeley, Microsoft Research, and Microsoft Security released the open-source plugin TokenEconomizer. The plugin learns from coding agents' historical sessions in repositories, reducing the token cost of subsequent sessions without modifying the agents or the underlying models. Across 277 SWE-Bench tasks and five agent-model combinations, average cost dropped by 18.4–30.9%; all 30 repository-combination pairings saved money and task success rates remained broadly stable; Web-Bench sequential development tasks cut costs by 16.0–21.2%, and security audit tasks by 6.4–19.6%. Its mechanisms include micro-skills that record repository-specific knowledge, pruning infrequently used tools, and having a judge model step in to suggest a change of approach when an agent gets repeatedly stuck.

AI-generated from public reports

Latest development · Report

Microsoft Research and others propose TokenEconomizer: enabling coding agents to learn from historical sessions to reduce token costs

Developments

1 confirmed developments

  1. Microsoft Research and others release open-source plugin TokenEconomizer

    Source:Microsoft Research

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Nov 17

  1. Microsoft ResearchFirst-partySelected

    Microsoft Research and others propose TokenEconomizer: enabling coding agents to learn from historical sessions to reduce token costs

    Microsoft Research, in collaboration with UC Berkeley and Microsoft Security, proposes an open-source plugin called TokenEconomizer, which learns from coding agents' historical sessions in repositories to reduce the token overhead of subsequent sessions without modifying the agents or the underlying models. Across 277 SWE-Bench tasks and five agent-model combinations, the average cost is reduced by 18.4–30.9%; all 30 repository-combination pairings save money, and task success rates remain generally stable. On Web-Bench sequential development tasks, costs are reduced by 16.0–21.2%, and on security audit tasks by 6.4–19.6%. The mechanisms include recording micro-skills of repository-specific knowledge, pruning infrequently used tools, and having a judge model step in to suggest a change of approach when an agent gets repeatedly stuck.

Related stories

  1. Related storiesGitHub Next introduces the PDD Kit and a login handling example
  2. Related storiesThe DeepSeek Harness team shares its Super-agent design exploration
  3. Related storiesSimon Willison introduces the sparqlite experimental project
  4. Related storiesXiaomi MiMo Releases MiMo-V2.6 Pro and Flash