# Preprint finds truthful error notes improve AI agent recovery

_Published Saturday, November 14, 2026 at 7:06 AM EST · AI, Science · Latest · Tier 2 — Notable_

A preprint reports that adding a truthful correction beside a preserved AI agent error improved recovery on AgentCE-Bench from 51% under a matched neutral note to 66%. Rewriting the history to portray the correction as a completed action instead lowered recovery from 50% with an unedited history to 44%.

Researchers froze agents mid-task, changed their histories or the surrounding task state, and let another model continue. In AppWorld, a success receipt lowered whole-task success from 45% to 28% when a database write's effect was absent, but raised it from 38% to 49% when the effect was present. The experiments show that a history edit's benefit depends on whether it accurately reflects the task's actual state.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2611.14654)

---
Canonical: https://techandbusiness.org/newswire/CP0JeKVPs3O56T3TO2K7Hb
Published: 2026-11-14T12:06:21.163Z
Story chronology: 2026-11-14T05:00:00.000Z
Retrieved: 2026-11-15T00:01:46.028Z
Publisher: Tech & Business (techandbusiness.org)