• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI
Report

TeleTune proposes learning agent skills from raw usage logs

A post describing a Microsoft paper says TeleTune keeps skill-library edits only when they improve next-action accuracy on held-out logs.

1 Source, 1h ago, first seen 1h ago

TLDR

A post describes TeleTune as a method for learning agent skills from offline usage logs. It says TeleTune guesses each session’s goal, predicts logged actions using a text skill library, and retains edits only when they improve next-action accuracy on held-out logs. The post says that measure tracked live success, suggesting a way to evaluate edits without a live test environment.

Combined views

—

1 Source, first seen 1h ago

— likes— comments— saves— reposts

Combined views

—

1 Source, first seen 1h ago

— likes— comments— saves— reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

1 Source

Rohan Paul@rohanpaul_aiNew Microsoft paper shows that agents can learn software skills from raw usage logs by keeping only skill edits that better predict users' next actions. i.e. You do not need a live test environment to check whether a new agent skill helps, because next-action accuracy on old logs tracked live success. Usage logs hold lots of know-how, but they record no goals, often mix several tasks, and cannot be replayed. Earlier methods, like Agent Workflow Memory, need goal-labeled examples or a live environment to test changes. TeleTune guesses each session's goal and has the model predict every logged action using a text skill library. Wrong guesses suggest library edits, and an edit stays only if accuracy rises on held-out logs. If your product records user activity, mine it for agent skills and judge each change by next-action accuracy on held-out logs. – arxiv. org/abs/2610.05437 Title: "TeleTune: Evolving Agent Skills From Offline Telemetry"1h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    1 Source

    Rohan Paul@rohanpaul_aiNew Microsoft paper shows that agents can learn software skills from raw usage logs by keeping only skill edits that better predict users' next actions. i.e. You do not need a live test environment to check whether a new agent skill helps, because next-action accuracy on old logs tracked live success. Usage logs hold lots of know-how, but they record no goals, often mix several tasks, and cannot be replayed. Earlier methods, like Agent Workflow Memory, need goal-labeled examples or a live environment to test changes. TeleTune guesses each session's goal and has the model predict every logged action using a text skill library. Wrong guesses suggest library edits, and an edit stays only if accuracy rises on held-out logs. If your product records user activity, mine it for agent skills and judge each change by next-action accuracy on held-out logs. – arxiv. org/abs/2610.05437 Title: "TeleTune: Evolving Agent Skills From Offline Telemetry"1h
    Today's Rank

    #15

    Today's Rank

    #15