alphaXiv(@askalphaxiv):“BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure” Reward hacking in agent benchmarks is often an infrastructure problem, not just a model-behavior problem. So this paper formalizes the full reward path and instruments runs to distinguish vulnerable tasks from actual exploit use, reaching 96% runtime detection accuracy and much higher exploit-chain recall than prior scanning baselines.

2026.09.13 14:00

“BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure” Reward hacking in agent benchmarks is often an infrastructure problem, not just a model-behavior problem. So this paper formalizes the full reward path and instruments runs to distinguish vulnerable tasks from actual exploit use, reaching 96% runtime detection accuracy and much higher exploit-chain recall than prior scanning baselines.

显示更多