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

• URL: http://arxiv.org/abs/2603.07084v1
• Date: Sat, 07 Mar 2026 07:43:14 GMT
• Title: Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
• Abstract summary: Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task.<n>We introduce Countdown-Code, a minimal environment where models can both solve a mathematical reasoning task and manipulate the test harness.<n>We study reward hacking in open-weight LLMs and find that such behaviors can be unintentionally learned during supervised fine-tuning.
• Score: 15.115899490498341
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning [38.94991079606593]
  We introduce CHERRL, a controllable hacking environment for rubric-based RL.<n>CHERRL enables stable reproduction of reward hacking, explicit observation of reward divergence, and precise identification of hacking onset.<n>To demonstrate its utility, we analyze different judge biases from the perspectives of discoverability and exploitability.
  arXiv  Detail & Related papers  (2026-06-03T14:18:23Z)
• Do Synthetic Trajectories Reflect Real Reward Hacking? A Systematic Study on Monitoring In-the-Wild Hacking in Code Generation [53.024513172383195]
  We present a systematic analysis of the synthetic vs. in-the-wild discrepancy in reward hacking.<n>We examine what extent hacking behaviors induced by prompting resemble those emerging during RL training.<n>We find that synthetic-data-trained monitors fail to generalize to "in-the-wild" hacking.
  arXiv  Detail & Related papers  (2026-04-26T01:26:50Z)
• Detecting and Suppressing Reward Hacking with Gradient Fingerprints [46.25008147178368]
  Fingerprint Gradient (GRIFT) is a method for detecting reward hacking using models' internal computations.<n>Across verifiable reasoning benchmarks, GRIFT substantially outperforms strong baselines.<n>Our results highlight a promising direction of leveraging gradient level representations for assessing the quality of CoT reasoning traces.
  arXiv  Detail & Related papers  (2026-04-17T17:01:24Z)
• When Reward Hacking Rebounds: Understanding and Mitigating It with Representation-Level Signals [11.280037154530847]
  Reinforcement learning for LLMs is vulnerable to reward hacking.<n>We study this phenomenon in coding tasks using an environment-manipulation setting.<n>We propose Advantage Modification, which integrates shortcut concept scores into GRPO advantage computation.
  arXiv  Detail & Related papers  (2026-04-01T23:33:08Z)
• IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking [67.20568716300272]
  Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking.<n>We introduce IR3 (Interpretable Reward Reconstruction and Rectification), a framework that reverse-engineers, interprets, and surgically repairs the implicit objectives driving RLHF-tuned models.<n>We show that IR3 achieves 0.89 correlation with ground-truth rewards, identifies hacking features with over 90% precision, and significantly reduces hacking behaviors while maintaining capabilities within 3% of the original model.
  arXiv  Detail & Related papers  (2026-02-23T01:14:53Z)
• Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking [69.06218054848803]
  We propose Adrial Reward Auditing (ARA), a framework that reconceptualizes reward hacking as a dynamic, competitive game.<n>ARA operates in two stages: first, a Hacker policy discovers reward model vulnerabilities while an Auditor learns to detect exploitation from latent representations.<n>ARA achieves the best alignment-utility tradeoff among all baselines.
  arXiv  Detail & Related papers  (2026-02-02T07:34:57Z)
• Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort [44.34183850072512]
  Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat.<n>To detect implicit reward hacking, we propose TRACE (Truncated Reasoning AUC Evaluation)<n>Our key observation is that hacking occurs when exploiting the loophole is easier than solving the actual task.
  arXiv  Detail & Related papers  (2025-10-01T18:49:45Z)
• School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs [10.660648055655022]
  Reward hacking is where agents exploit flaws in imperfect reward functions rather than performing tasks as intended.<n>We built a dataset containing over a thousand examples of reward hacking on low-stakes, self-contained tasks.<n>Our results provide preliminary evidence that models that learn to reward hack may generalize to more harmful forms of misalignment.
  arXiv  Detail & Related papers  (2025-08-24T20:23:08Z)
• Reward Shaping to Mitigate Reward Hacking in RLHF [47.71454266800376]
  Preference As Reward (PAR) is a novel approach that leverages the latent preferences embedded within the reward model as the signal for reinforcement learning.<n>On the AlpacaEval 2.0 benchmark, PAR achieves a win rate of at least 5 percentage points higher than competing approaches.
  arXiv  Detail & Related papers  (2025-02-26T02:57:59Z)
• Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking [11.589217788048964]
  We introduce a definition of reward hacking based on the correlation between proxy and true rewards for states.<n>We show theoretically that regularization to the reference policy can effectively prevent reward hacking.
  arXiv  Detail & Related papers  (2024-03-05T18:22:15Z)
• The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models [85.68751244243823]
  Reward hacking -- where RL agents exploit gaps in misspecified reward functions -- has been widely observed, but not yet systematically studied. We investigate reward hacking as a function of agent capabilities: model capacity, action space resolution, observation space noise, and training time. We find instances of phase transitions: capability thresholds at which the agent's behavior qualitatively shifts, leading to a sharp decrease in the true reward.
  arXiv  Detail & Related papers  (2022-01-10T18:58:52Z)
• Semi-supervised reward learning for offline reinforcement learning [71.6909757718301]
  Training agents usually requires reward functions, but rewards are seldom available in practice and their engineering is challenging and laborious. We propose semi-supervised learning algorithms that learn from limited annotations and incorporate unlabelled data. In our experiments with a simulated robotic arm, we greatly improve upon behavioural cloning and closely approach the performance achieved with ground truth rewards.
  arXiv  Detail & Related papers  (2020-12-12T20:06:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.