3 papers in the archive (2024–2026), average empirical rigor 6.2/10, average math complexity 4.7/10. Quadrant mix: Holy Grail ×1, Street Traders ×2.
Works mostly in Reinforcement Learning for Trading, Risk Management & Tail Risk, Fixed Income & Interest Rates, NLP & LLMs in Finance.
Frequent co-authors: Liqun Chen (2), Jin Zhao (1).
Scores are our LLM-assisted heuristics (methodology), not peer review or citation counts. Author pages are generated from paper metadata; name variants may split one person across pages. arXiv author page →
Ordered by a blend of empirical rigor (60%) and math complexity (40%).
The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, such as Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF), frequently induce model sycophancy, while execution-based environmen
Reality may establish that an outcome occurred without identifying which evolving procedure produced it or why. This distinction matters in production ML systems whose code, configuration, and artifacts change while external feedback accumulates. We examine it in a human-directed, agent-engineered q
In the field of finance, the prediction of individual credit default is of vital importance. However, existing methods face problems such as insufficient interpretability and transparency as well as limited performance when dealing with high-dimensional and nonlinear data. To address these issues, t