Copertina

Extending MONA in Camera Dropbox: Reproduction, Learned Approval, and Design Implications for Reward-Hacking Mitigation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Heath, Nathan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
di: Farquhar, Sebastian, et al.
Pubblicazione: (2025)

Reward Hacking Mitigation using Verifiable Composite Rewards
di: Tarek, Mirza Farhan Bin, et al.
Pubblicazione: (2025)

Repairing Reward Functions with Feedback to Mitigate Reward Hacking
di: Hatgis-Kessell, Stephane, et al.
Pubblicazione: (2025)

Reward Shaping to Mitigate Reward Hacking in RLHF
di: Fu, Jiayi, et al.
Pubblicazione: (2025)

Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking
di: Beigi, Mohammad, et al.
Pubblicazione: (2026)

ODIN: Disentangled Reward Mitigates Hacking in RLHF
di: Chen, Lichang, et al.
Pubblicazione: (2024)

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking
di: Singha, Disha
Pubblicazione: (2026)

Reward Hacking in Rubric-Based Reinforcement Learning
di: Mahmoud, Anas, et al.
Pubblicazione: (2026)

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
di: Miao, Yuchun, et al.
Pubblicazione: (2024)

IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
di: Beigi, Mohammad, et al.
Pubblicazione: (2026)

Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
di: Laidlaw, Cassidy, et al.
Pubblicazione: (2024)

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness
di: Ono, Shinnosuke, et al.
Pubblicazione: (2026)

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
di: Taylor, Mia, et al.
Pubblicazione: (2025)

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
di: Roth, Amit, et al.
Pubblicazione: (2026)

Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement
di: Gallego, Víctor
Pubblicazione: (2025)

Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment
di: Wang, Ye, et al.
Pubblicazione: (2026)

Spontaneous Reward Hacking in Iterative Self-Refinement
di: Pan, Jane, et al.
Pubblicazione: (2024)

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
di: Wang, Chaoqi, et al.
Pubblicazione: (2025)

Mitigating Preference Hacking in Policy Optimization with Pessimism
di: Gupta, Dhawal, et al.
Pubblicazione: (2025)

Reward Hacking as Equilibrium under Finite Evaluation
di: Wang, Jiacheng, et al.
Pubblicazione: (2026)

Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
di: Ackermann, Johannes, et al.
Pubblicazione: (2026)

LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
di: Helff, Lukas, et al.
Pubblicazione: (2026)

Natural Emergent Misalignment from Reward Hacking in Production RL
di: MacDiarmid, Monte, et al.
Pubblicazione: (2025)

Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning
di: Turpin, Miles, et al.
Pubblicazione: (2025)

Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
di: McKee-Reid, Leo, et al.
Pubblicazione: (2024)

RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents
di: Atinafu, Yonas, et al.
Pubblicazione: (2026)

Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
di: Ma, SHengjie, et al.
Pubblicazione: (2025)

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
di: Thaman, Kunvar
Pubblicazione: (2026)

Monitoring Emergent Reward Hacking During Generation via Internal Activations
di: Wilhelm, Patrick, et al.
Pubblicazione: (2026)

Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
di: Wang, Xinpeng, et al.
Pubblicazione: (2025)

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
di: Gan, Siyuan, et al.
Pubblicazione: (2026)

Feedback Loops With Language Models Drive In-Context Reward Hacking
di: Pan, Alexander, et al.
Pubblicazione: (2024)

GARDO: Reinforcing Diffusion Models without Reward Hacking
di: He, Haoran, et al.
Pubblicazione: (2025)

Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
di: Deshpande, Darshan, et al.
Pubblicazione: (2026)

SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
di: Zhao, Bingchen, et al.
Pubblicazione: (2026)

Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking
di: Rashidinejad, Paria, et al.
Pubblicazione: (2024)

Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
di: Khalifa, Muhammad, et al.
Pubblicazione: (2026)

Tiered Reward: Designing Rewards for Specification and Fast Learning of Desired Behavior
di: Zhou, Zhiyuan, et al.
Pubblicazione: (2022)

Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs
di: Sahoo, Subramanyam
Pubblicazione: (2026)

HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
di: Delfosse, Quentin, et al.
Pubblicazione: (2024)