arXiv (All)
open access
CheatBench: Measuring Reward Gaming in AI Agents
Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recent incidents and controlled evaluations across the AI industry, agents trained to maximize reward have accessed unauthorized information, attempted t
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- RMB: Reward Model Boosting Mitigates Reward Hacking#1117933
- Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics#1143448
- Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare#973158
- Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search#1078248
- Theoretical Considerations of Potential-Based Reward Shaping for Multi-Agent Systems#638157
Record · ID 1131150
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive