# DeXposure-Claw: An Agentic System for DeFi Risk Supervision

arXiv: https://arxiv.org/abs/2606.19501 · HTML: https://mlsanity.com/paper/2606.19501/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 18 of 18)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Temporal Graph Benchmark for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2307.01026/) (2023)
- [Turning Tabular Foundation Models into Graph Foundation Models](https://mlsanity.com/paper/2508.20906/) (2025)
- [LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management](https://mlsanity.com/paper/2501.00826/) (2025)
- [Know Your Intent: An Autonomous Multi-Perspective LLM Agent Framework for DeFi User Transaction Intent Mining](https://mlsanity.com/paper/2511.15456/) (2025)
- [Can Blindfolded LLMs Still Trade? An Anonymization-First Framework for Portfolio Optimization](https://mlsanity.com/paper/2603.17692/) (2026)
- [DeXposure: A Dataset and Benchmarks for Inter-protocol Credit Exposure in Decentralized Financial Networks](https://mlsanity.com/paper/2511.22314/) (2025)
- [Explain First, Trust Later: LLM-Augmented Explanations for Graph-Based Crypto Anomaly Detection](https://mlsanity.com/paper/2506.14933/) (2025)
- [LLM-Powered Detection of Price Manipulation in DeFi](https://mlsanity.com/paper/2510.21272/) (2025)
- [Heterogeneous Graph Pre-training Based Model for Secure and Efficient Prediction of Default Risk Propagation among Bond Issuers](https://mlsanity.com/paper/2501.03268/) (2025)
- [An Effective and Cost-Efficient Agentic Framework for Ethereum Smart Contract Auditing](https://mlsanity.com/paper/2601.17833/) (2026)
- [DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on Decentralized Financial Networks](https://mlsanity.com/paper/2602.03981/) (2026)
- [Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization](https://mlsanity.com/paper/2603.26270/) (2026)
- [Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation](https://mlsanity.com/paper/2606.02528/) (2026)

## Abstract (arXiv)

Decentralized finance exposes supervisors to fast-moving, networked credit risks. General-purpose LLM agents fit this setting poorly: they over-read weak evidence and recommend high-stakes interventions, while existing evaluations offer no regulator-aligned way to measure the resulting false alarms. We introduce DeXposure-Claw, a forecast-grounded agentic supervision system that routes LLM decisions through structured evidence: (1) DeXposure-FM, a graph time-series foundation model, forecasts future exposure networks; (2) deterministic monitors and stress scenarios then turn those forecasts into typed alerts, attribution signals, and scenario evidence; and (3) data-health and confidence gates constrain escalation before DeXposure-Claw emits auditable supervisory tickets with rationales. We further develop DeXposure-Bench, a six-axis evaluation harness, whose decision axis scores tickets against a regulator-aligned absolute-loss ground truth and an explicit false-intervention rate. Experiments on five years of weekly real data fully support our system. Code is at https://github.com/EVIEHub/DeXposure-Claw.