# Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR

arXiv: https://arxiv.org/abs/2603.07084 · HTML: https://mlsanity.com/paper/2603.07084/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Reward hacking and misspecification, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 7 Mar 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward hacking and misspecification](https://mlsanity.com/alignment/reward-hacking-and-misspecification/)

## Builds on (most cited first, 23 of 23)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models](https://mlsanity.com/paper/2201.03544/) (2022)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Natural Emergent Misalignment from Reward Hacking in Production RL](https://mlsanity.com/paper/2511.18397/) (2025)
- [LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!](https://mlsanity.com/paper/2502.07374/) (2025)
- [Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples](https://mlsanity.com/paper/2510.07192/) (2025)
- [LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs](https://mlsanity.com/paper/2504.14655/) (2025)
- [School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs](https://mlsanity.com/paper/2508.17511/) (2025)
- [ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases](https://mlsanity.com/paper/2510.20270/) (2025)
- [Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking](https://mlsanity.com/paper/2403.03185/) (2024)
- [Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment](https://mlsanity.com/paper/2510.05024/) (2025)
- [Goodhart's Law in Reinforcement Learning](https://mlsanity.com/paper/2310.09144/) (2023)
- [Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort](https://mlsanity.com/paper/2510.01367/) (2025)

## Built on by (most cited first, 17 of 17)

- [Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges](https://mlsanity.com/paper/2604.13602/) (2026)
- [SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents](https://mlsanity.com/paper/2605.21384/) (2026)
- [SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?](https://mlsanity.com/paper/2606.07682/) (2026)
- [Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning](https://mlsanity.com/paper/2606.04923/) (2026)
- [Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack](https://mlsanity.com/paper/2605.12673/) (2026)
- [Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale](https://mlsanity.com/paper/2605.20744/) (2026)
- [Before the Model Learns the Bug:Fuzzing RLVR Verifiers](https://mlsanity.com/paper/2606.01066/) (2026)
- [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)
- [Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents](https://mlsanity.com/paper/2607.24300/) (2026)
- [When Does a Video-Language Model Stop Watching? Reward Strength Controls the Formation and Reversal of Visual Shortcuts in Multimodal RLVR](https://mlsanity.com/paper/2606.22043/) (2026)
- [Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations](https://mlsanity.com/paper/2607.01181/) (2026)
- [RH-Detect: A Unified Benchmark for Reward Hacking Detection](https://mlsanity.com/paper/2610.10947/) (2026)
- [Verifier Errors in RLVR: Reward Hacking, Limits of Feedback, and Selective Control](https://mlsanity.com/paper/2609.35677/) (2026)
- [CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL](https://mlsanity.com/paper/2609.39533/) (2026)
- [Gradient Routing Localizes and Removes Unintended Behaviors in RL](https://mlsanity.com/paper/2610.17062/) (2026)
- [Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR](https://mlsanity.com/paper/2610.17824/) (2026)

## Abstract (arXiv)

Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often expensive or impossible to compute. We introduce Countdown-Code, a minimal environment where models can both solve a mathematical reasoning task and manipulate the test harness. This dual-access design creates a clean separation between proxy rewards (test pass/fail) and true rewards (mathematical correctness), enabling accurate measurement of reward-hacking rates. Using this environment, we study reward hacking in open-weight LLMs and find that such behaviors can be unintentionally learned during supervised fine-tuning (SFT) when even a small fraction of reward-hacking trajectories leak into training data. As little as 1% contamination in distillation SFT data is sufficient for models to internalize reward hacking which resurfaces during subsequent reinforcement learning (RL). We further show that RL amplifies misalignment and drives its generalization beyond the original domain. We open-source our environment and code to facilitate future research on reward hacking in LLMs. Our results reveal a previously underexplored pathway through which reward hacking can emerge and persist in LLMs, underscoring the need for more rigorous validation of synthetic SFT data. Code is available at https://github.com/zohaib-khan5040/Countdown-Code.