Newest papers

Back Up Before You Regret: Measuring Backup Awareness and Automating Backup in Coding Agents

Xu Li, Simon Yu, Minzhou Pan, Yiyou Sun, Zhaorun Chen, Bo Li, Weiyan Shi · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28934 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Агенты-кодировщики теперь выполняют задачи автономно, модифицируя реальное состояние, такие как артефакты, программные среды и конфигурации по пути. Тем не менее, они демонстрируют ограниченное осознание задач резервного копирования: признавая, что основное действие будет модифицировать состояние, которое может понадобиться позже, и сохраняя его заранее. Чтобы оценить осведомленность о резервном копировании, мы вводим RegretBench, ориентир из 205 выполняемых задач, основанных на моментах сожаления, сообщаемых на платформах, таких как X.com, GitHub и Stack Overflow, где пользователи явно сожалеют о том, что не сохранили состояние затрат, которые им понадобились позже. На протяжении шести моделей границ агенты выполняют 86,1%

Machine translation (Meta M2M100); the English original follows.

Abstract

Coding agents now complete tasks autonomously, modifying real-world state such as artifacts, software environments, and configurations along the way. Yet they show limited backup awareness: recognizing that an action will modify state that may later be needed, and preserving it beforehand. To evaluate backup awareness, we introduce RegretBench, a benchmark of 205 executable tasks grounded in regret moments reported on platforms such as X.com, GitHub, and Stack Overflow, where users explicitly regretted not preserving state they later needed. Across six frontier models, agents complete 86.1% of tasks on average yet back up before these moments in only 15.2%, showing that task completion ability does not imply backup awareness. Because it is hard to predict which changes will be regretted, we propose BackUpper, a harness plug-in backup layer that checks every tool call and preserves affected state before modification. It combines rule-based strategies for common operations with a lightweight subagent for complex cases, and its rule table can expand with subagent decisions over time. On RegretBench, BackUpper covers every regret moment action and restores states with 92.2% average similarity to the original. Achieving this costs only $0.014 per task, with 7x fewer tokens than the main-agent self-backup baseline. When users have preferences on what to back up, BackUpper can also narrow its scope accordingly, matching human annotations on whether an action is worth preserving with an 84.5% F1 score. These results suggest that agents can keep actions reversible at low cost while respecting users' preferences.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Backup, Computer science, Oracle, Leverage (statistics), Coding (social sciences), Regret

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange