Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks

2026-08-22

AI Summary

研究通过引入Hack-Verifiable Terminal Bench方法，自动检测并评估智能体在终端任务中的奖励作弊行为，并测试不同提示信息对减少该行为的效果。

Abstract

As agents grow more capable and autonomous, their tendency to reward hack, satisfying a task's checks while violating its intent, becomes an increasingly important failure mode. Measuring reward hacking is itself challenging, as detection typically relies on human inspection or LLM judges, both of which can be unreliable. The hack-verifiable environments (HVE) methodology addresses this challenge by embedding detectable hacks into tasks, allowing reward hacks to be identified automatically and reliably. In this work, we adapt HVE to Terminal Bench, a leading benchmark of real-world terminal and coding tasks, and introduce Hack-Verifiable Terminal Bench (HVTB). Using HVTB, we measure reward-hacking rates across frontier models and study whether prompts with varying amounts of information on the hack can mitigate this behavior. This lets us test whether prompting can prevent not only known reward-hacking strategies, but also 'unknown unknown' exploits that the prompt does not anticipate. We release all environments and agent traces at https://majoroth.github.io/hack-verifiable-environments/hvtb

Problem

• reward hacking
• autonomous agents
• failure mode
• human inspection
• LLM judges

Innovation

• Hack-Verifiable Environments
• Reward Hacking
• Automatic Detection
• Prompting Strategies