Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale

• URL: http://arxiv.org/abs/2605.20744v1
• Date: Wed, 20 May 2026 05:46:52 GMT
• Title: Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
• Abstract summary: We introduce a new evaluation paradigm for measuring reward hacking.<n>We embed detectable reward hacking opportunities directly into environments.<n>This makes their exploitation verifiable by design, enabling deterministic and automated measurement.
• Score: 16.00357530754102
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended objective. Reward hacking has been observed across a wide range of settings, yet methods for reliably measuring it at scale remain lacking. In this work, we introduce a new evaluation paradigm for measuring reward hacking. Whereas prior studies have primarily analyzed it post hoc by inspecting agent trajectories, we instead embed detectable reward hacking opportunities directly into environments. This makes their exploitation verifiable by design, enabling deterministic and automated measurement of whether and how agents exploit such vulnerabilities. We instantiate this approach in $\textit{TextArena}$ and release $\textit{Hack-Verifiable TextArena}$, a testbed in which reward hacking can be measured reliably. Using this benchmark, we analyze reward hacking behavior across language models in diverse environments and settings. We open source the code at https://github.com/MajoRoth/hack-verifiable-environments/.

Related papers

• Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks [14.722822786841357]
  Hack-verifiable environments (HVE) embed detectable hacks into tasks, allowing reward hacks to be identified automatically and reliably.<n>We adapt HVE to Terminal Bench, a leading benchmark of real-world terminal and coding tasks, and introduce Hack-Verifiable Terminal Bench (HVTB)<n>HVTB measures reward-hacking rates across frontier models and study whether prompts with varying amounts of information on the hack can mitigate this behavior.
  arXiv  Detail & Related papers  (2026-08-22T20:59:36Z)
• 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)
• Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR [15.115899490498341]
  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.
  arXiv  Detail & Related papers  (2026-03-07T07:43:14Z)
• 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)
• EvilGenie: A Reward Hacking Benchmark [0.6533497575282355]
  EvilGenie is a benchmark for reward hacking in programming settings.<n>We measure reward hacking in three ways: held out unit tests, LLM judges, and test file edit detection.
  arXiv  Detail & Related papers  (2025-11-26T18:27:17Z)
• Bag of Tricks for Subverting Reasoning-based Safety Guardrails [62.139297207938036]
  We present a bag of jailbreak methods that subvert the reasoning-based guardrails.<n>Our attacks span white-, gray-, and black-box settings and range from effortless template manipulations to fully automated optimization.
  arXiv  Detail & Related papers  (2025-10-13T16:16:44Z)
• 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)
• Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection [62.595450266262645]
  This paper introduces a novel and previously unrecognized threat in face forgery detection scenarios caused by backdoor attack. By embedding backdoors into models, attackers can deceive detectors into producing erroneous predictions for forged faces. We propose emphPoisoned Forgery Face framework, which enables clean-label backdoor attacks on face forgery detectors.
  arXiv  Detail & Related papers  (2024-02-18T06:31:05Z)
• Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark [61.43264961005614]
  We develop a benchmark of 134 Choose-Your-Own-Adventure games containing over half a million rich, diverse scenarios. We evaluate agents' tendencies to be power-seeking, cause disutility, and commit ethical violations. Our results show that agents can both act competently and morally, so concrete progress can be made in machine ethics.
  arXiv  Detail & Related papers  (2023-04-06T17:59:03Z)

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.