Accounting-Aware Evidence-Constrained Agents for Disclosure, Settlement, and Secondary-Market Risk Monitoring in Tokenized

Sihan  Zhou; Yuanzheng  Chen; Kenny  Lee

doi:10.51903/jtie.v5i2.544

Authors

Sihan Zhou Enterprise Risk Management, Columbia University, NY, USA
Yuanzheng Chen Accounting, UIUC, IL, USA
Kenny Lee Applied Analytics, Columbia University, NY, USA

DOI:

https://doi.org/10.51903/jtie.v5i2.544

Keywords:

Accounting-aware agent, Evidence-constrained monitoring, RWA protocol TVL, Settlement risk, Tokenized real-world assets

Abstract

Tokenized real-world asset (RWA) infrastructure exposes platform operators, investors, and reporting teams to a combined settlement, disclosure, liquidity, and accounting-quality monitoring problem. A tokenized claim can continue to trade while the underlying issuer releases new financial statements, securities fail to deliver in the reference market, or protocol-level liquidity changes in RWA venues. This paper develops an accounting-aware, evidence-constrained agent workflow for risk alerting and source-grounded report generation. The revised experiment replaces the earlier rule-generated monitoring sandbox with external datasets: SEC fails-to-deliver observations, SEC EDGAR XBRL company facts, SEC submissions metadata, Financial PhraseBank sentiment labels, and DefiLlama RWA protocol TVL. The issuer-day panel contains 2,648 surveillance tasks for eight large U.S. issuers from 2024-12-01 through 2026-03-31. Observed settlement stress is defined from external SEC FTD balances rather than from the agent's own rule. Accounting risk is computed from XBRL-derived liquidity, leverage, accrual, and cash-flow indicators. A stronger market-plus-accounting logistic baseline is added alongside single-source baselines and the proposed fusion agent. The machine-learning baseline achieves the strongest F1 score for settlement-stress detection (0.909), while the proposed fusion agent achieves the highest report faithfulness and tool-use correctness (1.000 each) and high recall (0.849). The results support a governance-oriented interpretation: an evidence-constrained agent is most useful not as an opaque high-accuracy classifier, but as an auditable layer that connects settlement evidence, filing metadata, accounting fundamentals, independent sentiment calibration, and RWA protocol liquidity into a reproducible monitoring record.

References

Amihud, Y. (2002). Illiquidity and stock returns: Cross-section and time-series effects. Journal of Financial Markets, 5(1), 31-56.

Araci, D. (2019). FinBERT: Financial sentiment analysis with pre-trained language models. arXiv:1908.10063.

Bank for International Settlements. (2023). Blueprint for the future monetary system: Improving the old, enabling the new. BIS Annual Economic Report.

Bank for International Settlements. (2024). Tokenisation in the context of money and other assets: Concepts and implications for central banks. BIS.

Brunnermeier, M. K., & Pedersen, L. H. (2009). Market liquidity and funding liquidity. Review of Financial Studies, 22(6), 2201-2238.

Cong, L. W., & He, Z. (2019). Blockchain disruption and smart contracts. Review of Financial Studies, 32(5), 1754-1797.

DefiLlama. (2026). DefiLlama API and methodology documentation. https://api-docs.defillama.com/

Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023). Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12), 1-38.

Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Kuttler, H., Lewis, M., Yih, W.-t., Rocktaschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459-9474.

Malo, P., Sinha, A., Korhonen, P., Wallenius, J., & Takala, P. (2014). Good debt or bad debt: Detecting semantic orientations in economic texts. Journal of the Association for Information Science and Technology, 65(4), 782-796.

Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020). On faithfulness and factuality in abstractive summarization. Proceedings of ACL, 1906-1919.

OECD. (2020). The tokenisation of assets and potential implications for financial markets. OECD Blockchain Policy Series.

O'Hara, M. (1995). Market microstructure theory. Blackwell.

Pastor, L., & Stambaugh, R. F. (2003). Liquidity risk and expected stock returns. Journal of Political Economy, 111(3), 642-685.

Schar, F. (2021). Decentralized finance: On blockchain- and smart contract-based financial markets. Federal Reserve Bank of St. Louis Review, 103(2), 153-174.

Securities and Exchange Commission. (2026a). Fails-to-deliver data. https://www.sec.gov/data-research/sec-markets-data/fails-deliver-data

Securities and Exchange Commission. (2026b). EDGAR application programming interfaces. https://www.sec.gov/search-filings/edgar-application-programming-interfaces

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.

Wu, S., Irsoy, O., Lu, S., Dabravolski, V., Dredze, M., Gehrmann, S., Kambadur, P., Rosenberg, D., & Mann, G. (2023). BloombergGPT: A large language model for finance. arXiv:2303.17564.

Xie, Q., Han, W., Chen, X., Lai, Y., Zhang, M., Peng, M., Lopez-Lira, A., & Huang, J. (2023). PIXIU: A large language model, instruction data and evaluation benchmark for finance. arXiv:2306.05443.

Yang, H., Liu, X.-Y., & Wang, C. D. (2023). FinGPT: Open-source financial large language models. arXiv:2306.06031.

Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. International Conference on Learning Representations.