Newest papers

Automating Feature Flag Cleanup at Scale with Multi-Agent LLM Systems: An Industrial Experience at DoorDash

Atharv Chandratre, Jai Datar · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31351 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Флаг и его шифрованный код становятся техническим долгом и могут вводить операционный риск путем непреднамеренного разрешения кодовых путей. В DoorDash более 56 000 флаг и шифрованные флаги охватывают 623 хранилища, с 1 659 в настоящее время заблокированными по состоянию на май 2026 года, с внутренними оценками от одного до двух часов за ручную чистку. Существующие инструменты очистки на основе правил оказались недостаточными в кодовых базах DoorDash. Наш вклад - это автоматизированная система очистки флагов на основе LLM, которая интегрирует запросы на живые флаг и шифрование данных с использованием процессов MCP Jira, а также создание запросов на очистку от конца до конца. Наша система успешно производила аналоги

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

Abstract

Feature flags are runtime configuration mechanisms used for gradual feature rollouts, experimentation, and kill switches. Once a feature is fully rolled out, the flag and its gated code become technical debt and can introduce operational risk through inadvertently enabling dormant code paths. At DoorDash, over 56,000 feature flags span 623 repositories, with 1,659 currently stale as of May 2026, with internal estimates of one to two hours per manual cleanup. Existing rule-based cleanup tools proved insufficient in DoorDash's codebases. Our contribution is an end-to-end automated LLM-based feature flag cleanup system that integrates querying live feature flag rollout data using MCP, Jira ticket processing, and end-to-end pull request creation. Our system successfully produced engineer-approved flag removal PRs for 45 (90%) of the 50 stale flags it was evaluated on, proving the system's operational viability at scale with each cleanup averaging only $4.79 and 13.8 minutes. We evaluated the system's quality and reliability boundary based on success rates, cost per cleanup and time metrics. Furthermore, we discuss our lessons learned when architecting this system, to provide practical guidance for developing similar multi-agent systems.

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

Topics: Flag (linear algebra), FLAGS register, Feature (linguistics), Computer science, Scale (ratio), Reliability (semiconductor)

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31351, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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