ZORO: Active Rules for Reliable Vibe Coding
Jenny Ma, Sitong Wang, Joshua H. Kung, Lydia B. Chilton
TLDR
ZORO transforms passive rules into active controls for coding agents, integrating them into every step to improve human-agent alignment and rule following.
Key contributions
- Integrates rules directly into coding agent workflows, anchoring them to every step.
- Enforces rules by requiring agents to prove compliance during implementation.
- Enables in-situ user feedback to iteratively evolve and refine rulesets.
- Significantly improves agent rule following and alters human coding strategies.
Why it matters
This paper addresses the challenge of human-agent alignment in "vibe coding" by making rules active rather than passive. By integrating rule enforcement and feedback directly into the agent's workflow, ZORO enhances reliability and opens new avenues for improving human-agent collaboration in coding and beyond.
Original Abstract
Rules files (e.g., AGENTS.md, CLAUDE.md) are the primary mechanism for human-agent alignment when developers vibe code. However, they remain passive: it is not immediately apparent when rules are being used or followed, or how to improve them. To transform rules from passive text into active controls, we introduce ZORO, an interactive interface that integrates directly with a coding agent and anchors rules to every step of the coding process. After an agent generates an initial plan, ZORO enriches the plan with rules, enforces the rules during implementation by requiring the agent prove that each rule was followed, and allows users to provide in-situ feedback when they are unsatisfied with a rule application to evolve the ruleset. A technical evaluation shows that coding agents follow rules more with ZORO than without. A user study demonstrates a change in people's behavior and cognitive strategies when rules are at the forefront of vibe coding. We discuss how making rules active in agentic systems unlocks broader opportunities for human-agent alignment in coding settings and beyond.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.