Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
arXiv:2510.10931v3 Announce Type: replace Abstract: While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking. Unlike execution-based tools (e.g., code or math), whose effects are directly observable, the weak observability of causal dependencies between retrieved evidence and reasoning under format- and outcome-level supervision enables agents to maximize surface-level reward signal…