collaborators

7 papers

cs.CE2026

No Certificate, No Execution: Certified Traces as a Foundation for Trustworthy AI Agents

Xiao-Yang Liu Yanglet, Xiaodong Wang, Agostino Capponi

We argue that trustworthy AI agents, especially in high-stakes and policy-governed domains, should make execution conditional on certified traces rather than rely only on stronger…

cs.CE2026

Evaluation and Benchmarking Suite for Financial Large Language Models and Agents

Shengyuan Lin, Kaiwen He, Jaisal Patel +10

Over the past three years, the financial services industry has witnessed Large Language Models (LLMs) and agents transitioning from the exploration stage to readiness and governanc…

cs.CE2025

FinRL Contests: Benchmarking Data-driven Financial Reinforcement Learning Agents

Keyi Wang, Nikolaus Holzer, Ziyi Xia +5

Financial reinforcement learning (FinRL) is now a practical paradigm for financial engineering. However, applying RL strategies to real-world trading tasks remains a challenge for…

cs.CE2025

Multimodal Financial Foundation Models (MFFMs): Progress, Prospects, and Challenges

Xiao-Yang Liu Yanglet, Yupeng Cao, Li Deng

Financial Large Language Models (FinLLMs), such as open FinGPT and proprietary BloombergGPT, have demonstrated great potential in select areas of financial services. Beyond this ea…

cs.CE2025

Open FinLLM Leaderboard: Towards Financial AI Readiness

Shengyuan Colin Lin, Felix Tian, Keyi Wang +9

Financial large language models (FinLLMs) with multimodal capabilities are envisioned to revolutionize applications across business, finance, accounting, and auditing. However, rea…

cs.CE2025

Revisiting Ensemble Methods for Stock Trading and Crypto Trading Tasks at ACM ICAIF FinRL Contest 2023-2024

Nikolaus Holzer, Keyi Wang, Kairong Xiao +1

Reinforcement learning has demonstrated great potential for performing financial tasks. However, it faces two major challenges: policy instability and sampling bottlenecks. In this…