Pomona: Continuous Code Quality Improvement via Small, Agentic Pull Requests at Bloomberg
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
In this industrial experience paper, we present Pomona, a lightweight agentic tool that utilises agent skills for continuous code quality improvement. Inspired by the Kaizen (TM) philosophy, Pomona automates a cycle of discovery and incremental repair: a Scanning skill identifies tasks and prioritises them in a backlog, while a Repair skill generates small, easily reviewable pull requests (PRs). This design enables frequent, low-risk improvements while maintaining engineer trust and reducing technical debt. We evaluated Pomona at Bloomberg through a three-month team deployment and a questionnaire distributed to senior engineers. The results are promising: 32/39 PRs (82.1%) were merged with a median time-to-close of just over two hours. Moreover, 10/12 surveyed engineers expressed a desire to adopt Pomona, praising its small diff sizes and focus on code quality. Since our evaluation, another team has adopted Pomona. We conclude with actionable insights for deploying agents in industry.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 14 of its 19 references that are in the map. First posted on arXiv 4 Jun 2026.
Builds on
14 of 19 references.
Closest ancestors · 6
Same direction, newest first
- 2026SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering10 Apr
- 2026SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?16 Mar
- 2025Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects6 Nov
- 2024SpecRover: Code Intent Extraction via LLMs5 Aug
- 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agents23 Jul
- 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May
Other references · 8
- 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Taskscited by 289
- 2023The Impact of AI on Developer Productivity: Evidence from GitHub Copilotcited by 264
- 2026EvoSkill: Automated Skill Discovery for Multi-Agent Systemscited by 96
- 2026Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scalecited by 94
- 2025Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivitycited by 93
- 2026SkillNet: Create, Evaluate, and Connect AI Skillscited by 48
- 2026"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wildcited by 46
- 2023User-Centric Deployment of Automated Program Repair at Bloombergcited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
- 2026AI builds, We Analyze: An Empirical Study of AI-Generated Build Code Quality
- 2026Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
- 2024Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios
- 2026Why Are AI Agent Involved Pull Requests (Fix-Related) Remain Unmerged? An Empirical Study
- 2026Not All Agents Are Equal: Code Quality and Post-Merge Maintenance Across Five Autonomous Coding Agents in the Wild
- 2026Evaluating Agent Skills for Version-Specific Plugin Migration: A Retrospective Study
- 2026Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs