arXiv Artificial Intelligence

After the Fix: Transfer of Corrected Agent Experience

2 hours ago 30.09.2026 07:00 👁 2 views
After the Fix: Transfer of Corrected Agent Experience

Quick summary

arXiv:2609.34603v2 Announce Type: replace Abstract: Does repairing an episode make its experience a better memory for the next task? We transfer the same failed source before and after accepted repair to a fixed target, alongside independent execution. Our 3,300 runs cover 100 ThinkingBox pairs and the same 100 APEX pairs with and without source-state inheritance, under eleven conditions. ThinkingBox's Full/Skill/Hybrid correction gains are 44/29/32 percentage points, with corrected performance 25/22/18 points above independence; inference weakens at the task-family level. Yet 12 of Full's 15-

Key takeaways

  • arXiv:2609.34603v2 Announce Type: replace Abstract: Does repairing an episode make its experience a better memory for the next task?
  • We transfer the same failed source before and after accepted repair to a fixed target, alongside independent execution.
  • Our 3,300 runs cover 100 ThinkingBox pairs and the same 100 APEX pairs with and without source-state inheritance, under eleven conditions.

Why it matters

The importance of “After the Fix: Transfer of Corrected Agent Experience” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗