Agentic Trading: When LLM Agents Meet Financial Markets
The paper titled 'Agentic Trading: When LLM Agents Meet Financial Markets' explores the integration of Large Language Models (LLMs) in trading systems. It highlights the challenges of protocol incomparability and the lack of reproducibility in existing studies. The authors suggest that while architectural experimentation is growing, the field faces significant bottlenecks in evaluation protocols and reproducible artifacts.
- ▪The paper presents an audit-oriented evidence map of 77 studies related to LLM-based trading agents.
- ▪Only 2 out of 19 studies in the primary empirical subset report extractable time-consistent split protocols.
- ▪The authors emphasize the need for improved evaluation protocols and reproducibility in the field.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.19337 (cs) [Submitted on 19 May 2026] Title:Agentic Trading: When LLM Agents Meet Financial Markets Authors:Yihan Xia, Panpan You, Taotao Wang, Fang Liu, Han Qi, Xiaoxiao Wu, Shengli Zhang View a PDF of the paper titled Agentic Trading: When LLM Agents Meet Financial Markets, by Yihan Xia and 6 other authors View PDF HTML (experimental) Abstract:A growing body of work explores how Large Language Models (LLMs) can be embedded in trading systems as agents that perceive market information, retrieve context, reason about decisions, emit tradable actions, and adapt under market feedback.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
