7 papers
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…
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…
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…
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…
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…
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…