# Before the Model Learns the Bug:Fuzzing RLVR Verifiers

arXiv: https://arxiv.org/abs/2606.01066 · HTML: https://mlsanity.com/paper/2606.01066/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 6 references that are in the map.
- First posted on arXiv 31 May 2026.

## Builds on (most cited first, 5 of 5)

- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking](https://mlsanity.com/paper/2604.15149/) (2026)
- [Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR](https://mlsanity.com/paper/2603.07084/) (2026)

## Built on by (most cited first, 7 of 7)

- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR](https://mlsanity.com/paper/2607.11022/) (2026)
- [Judging Is Not Enumerating: Silent Omissions in LLM-Authored Acceptable Sets](https://mlsanity.com/paper/2608.01000/) (2026)
- [No Free Checker: A Survey of Verifiers for Robot Policies](https://mlsanity.com/paper/2609.09250/) (2026)
- [From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents](https://mlsanity.com/paper/2609.36161/) (2026)
- [When a Data Artifact Isn't a Shortcut: Causal Auditing of Synthetic RLVR Corpora](https://mlsanity.com/paper/2610.00202/) (2026)
- [NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents](https://mlsanity.com/paper/2610.03631/) (2026)

## Abstract (arXiv)

Reinforcement learning with verifiable rewards (RLVR) replaces human preference labels with executable reward functions such as math answer checkers, JSON tool-call validators, and code unit-test harnesses. That makes the reward partly a software artifact: if the verifier is wrong, optimization can learn the bug. We study this failure mode with a lightweight verifier-fuzzing framework that generates adversarial completions, compares buggy and stricter reference verifiers, logs paired decisions, and reports false-positive, false-negative, disagreement, exploit, and uncertainty metrics.