Image de couverture de livre

RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Atinafu, Yonas, Cohen, Robin
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improving LLM Performance Through Black-Box Online Tuning: A Case for Adding System Specs to Factsheets for Trusted AI
par: Atinafu, Yonas, et autres
Publié: (2026)

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

LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild
par: Reworr, et autres
Publié: (2024)

LLM Agents can Autonomously Hack Websites
par: Fang, Richard, et autres
Publié: (2024)

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
par: Roth, Amit, et autres
Publié: (2026)

ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
par: Liu, Zexi, et autres
Publié: (2025)

SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
par: Zhao, Bingchen, et autres
Publié: (2026)

PixLift: Accelerating Web Browsing via AI Upscaling
par: Atinafu, Yonas, et autres
Publié: (2025)

Hacking CTFs with Plain Agents
par: Turtayev, Rustem, et autres
Publié: (2024)

Reward Hacking as Equilibrium under Finite Evaluation
par: Wang, Jiacheng, et autres
Publié: (2026)

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
par: Taylor, Mia, et autres
Publié: (2025)

HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing
par: Muzsai, Lajos, et autres
Publié: (2024)

Evaluation and Benchmarking of LLM Agents: A Survey
par: Mohammadi, Mahmoud, et autres
Publié: (2025)

Reward Hacking in Rubric-Based Reinforcement Learning
par: Mahmoud, Anas, et autres
Publié: (2026)

MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Evaluation of Language Model Agents
par: Wang, Shouju, et autres
Publié: (2026)

Reward Hacking Mitigation using Verifiable Composite Rewards
par: Tarek, Mirza Farhan Bin, et autres
Publié: (2025)

Repairing Reward Functions with Feedback to Mitigate Reward Hacking
par: Hatgis-Kessell, Stephane, et autres
Publié: (2025)

Reward Shaping to Mitigate Reward Hacking in RLHF
par: Fu, Jiayi, et autres
Publié: (2025)

Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
par: Deshpande, Darshan, et autres
Publié: (2026)

LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
par: Qiu, Jielin, et autres
Publié: (2025)

Fighting AI with AI: AI-Agent Augmented DNS Blocking of LLM Services during Student Evaluations
par: Kassa, Yonas, et autres
Publié: (2026)

Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking
par: Beigi, Mohammad, et autres
Publié: (2026)

Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards
par: Da, Jeff, et autres
Publié: (2025)

Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
par: Ma, SHengjie, et autres
Publié: (2025)

Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents
par: Jeurissen, Dominik, et autres
Publié: (2024)

Spontaneous Reward Hacking in Iterative Self-Refinement
par: Pan, Jane, et autres
Publié: (2024)

RRO: LLM Agent Optimization Through Rising Reward Trajectories
par: Wang, Zilong, et autres
Publié: (2025)

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
par: Wang, Chaoqi, et autres
Publié: (2025)

Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
par: Kim, Juhee, et autres
Publié: (2025)

The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination
par: Su, Haoran, et autres
Publié: (2026)

AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering
par: Zhang, Di
Publié: (2026)

Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents
par: Deng, Shihan, et autres
Publié: (2024)

AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
par: Jiang, Tanqiu, et autres
Publié: (2026)

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
par: Lù, Xing Han, et autres
Publié: (2025)

Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents
par: Shu, Jiangming, et autres
Publié: (2026)

AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning
par: Ding, Liang
Publié: (2026)

SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems
par: Yang, Zonglin, et autres
Publié: (2026)

AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
par: Trirat, Patara, et autres
Publié: (2024)

Benchmarking LLM Agents for Wealth-Management Workflows
par: Milsom, Rory
Publié: (2025)

Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents
par: Wang, Yiding, et autres
Publié: (2025)