# Preprint reports agent success gains from saving corrections in adapters

_Published Monday, October 26, 2026 at 3:32 PM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers report in a preprint that Self-Direction, a method for retaining lessons from failed tasks, improved Qwen-based agents' success rates by 8.9 to 17.0 percentage points across research, tool-use and terminal benchmarks.

After a failure, the agent reviews its actions, extracts a lesson and trains a small adapter while keeping the original model weights frozen. Each adapter adds parameters equivalent to ~0.02% of the base model's parameter count. The agent stores adapters in a library and selects them for related tasks later. The reported experiments cover GAIA, Claw-Eval and Terminal-Bench 2.1 using open-weight Qwen-family models.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2610.31846)

---
Canonical: https://techandbusiness.org/newswire/l706K0XgK9bI0y0H69hF1H
Published: 2026-10-26T19:32:40.195Z
Story chronology: 2026-10-26T04:00:00.000Z
Retrieved: 2026-10-26T21:32:54.916Z
Publisher: Tech & Business (techandbusiness.org)