Proof-of-Use: Mitigating tool-call hacking in Deep Research Agents

@article{shengjie2026,
  title = {Proof-of-Use: Mitigating tool-call hacking in Deep Research Agents},
  author = {Ma, Shengjie and Deng, Chenlong and Mao, Jiaxin and Huang, Jiadeng and Jiang, Xuhui and Wang, Teng and Wu, Junjie and Zhang, Changwang and Wang, Jun},
  journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year = {2026},
  month = {Jan},
  doi = {10.18653/2026.emnlp-main.1664},
  url = {https://doi.org/10.18653/2026.emnlp-main.1664},
}

Ma, Shengjie et al. (2026). Proof-of-Use: Mitigating tool-call hacking in Deep Research Agents. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/2026.emnlp-main.1664

Ma, Shengjie, et al.. "Proof-of-Use: Mitigating tool-call hacking in Deep Research Agents." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026, https://doi.org/10.18653/2026.emnlp-main.1664.

Ma, Shengjie, et al.. "Proof-of-Use: Mitigating tool-call hacking in Deep Research Agents." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (2026). https://doi.org/10.18653/2026.emnlp-main.1664

Ma, Shengjie et al., 2026. Proof-of-Use: Mitigating tool-call hacking in Deep Research Agents. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. Available at: <https://doi.org/10.18653/2026.emnlp-main.1664>.

TY  - JOUR
TI  - Proof-of-Use: Mitigating tool-call hacking in Deep Research Agents
AU  - Ma, Shengjie
AU  - Deng, Chenlong
AU  - Mao, Jiaxin
AU  - Huang, Jiadeng
AU  - Jiang, Xuhui
AU  - Wang, Teng
AU  - Wu, Junjie
AU  - Zhang, Changwang
AU  - Wang, Jun
PY  - 2026
JO  - Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
DO  - 10.18653/2026.emnlp-main.1664
UR  - https://doi.org/10.18653/2026.emnlp-main.1664
ER  -