An adaptive prompt-optimization framework that improves coordination and decision quality among LLM-based trading agents in dynamic markets.
@inproceedings{papadakis2026atlas,title={{ATLAS}: Adaptive Trading with {LLM} Agents Through Dynamic Prompt Optimization and Multi-Agent Coordination},author={Papadakis, Charidimos and Dimitriou, Angeliki and Filandrianos, Giorgos and Lymperaiou, Maria and Thomas, Konstantinos and Stamou, Giorgos},booktitle={Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL)},year={2026},}
2025
preprint
StockSim: A Dual-Mode Order-Level Simulator for Evaluating Multi-Agent LLMs in Financial Markets
Charidimos Papadakis, Giorgos Filandrianos, Angeliki Dimitriou, and 3 more authors
2025
Planned for submission to EMNLP 2026 System Demonstrations Track
A high-fidelity, dual-mode simulation environment for reproducible evaluation of LLM agent strategies and behavior under realistic order flows.
@misc{papadakis2025stocksim,title={{StockSim}: A Dual-Mode Order-Level Simulator for Evaluating Multi-Agent {LLM}s in Financial Markets},author={Papadakis, Charidimos and Filandrianos, Giorgos and Dimitriou, Angeliki and Lymperaiou, Maria and Thomas, Konstantinos and Stamou, Giorgos},year={2025},note={Planned for submission to EMNLP 2026 System Demonstrations Track},}