Cover Image

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Thaman, Kunvar
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts
by: Haimes, Jacob, et al.
Published: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
by: Andriushchenko, Maksym, et al.
Published: (2024)

ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
by: Lu, Jiarui, et al.
Published: (2024)

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

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking
by: Singha, Disha
Published: (2026)

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

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

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

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

Process Reward Models for LLM Agents: Practical Framework and Directions
by: Choudhury, Sanjiban
Published: (2025)

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

LuckyMera: a Modular AI Framework for Building Hybrid NetHack Agents
by: Quarantiello, Luigi, et al.
Published: (2023)

Evaluation and Benchmarking of LLM Agents: A Survey
by: Mohammadi, Mahmoud, et al.
Published: (2025)

Recoverability Has a Law: The ERR Measure for Tool-Augmented Agents
by: Vuddanti, Sri Vatsa, et al.
Published: (2026)

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

Exploiting LLM Quantization
by: Egashira, Kazuki, et al.
Published: (2024)

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
by: Li, Sijia, et al.
Published: (2025)

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

Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents
by: Xia, Fanzeng, et al.
Published: (2024)

LLM Agents Making Agent Tools
by: Wölflein, Georg, et al.
Published: (2025)

ToolRL: Reward is All Tool Learning Needs
by: Qian, Cheng, et al.
Published: (2025)

Widening the Gap: Exploiting LLM Quantization via Outlier Injection
by: Zhan, Xiaohua, et al.
Published: (2026)

FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction
by: Zeng, Zhiyuan, et al.
Published: (2025)

MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
by: Luo, Tianyang, et al.
Published: (2026)