arXiv releases research paper on agentic AI in automated markets
Get up to speed
A research team led by Irene Aldridge et al. has published a paper on arXiv studying the behavioral impact of AI agents in automated markets, constructing behavioral models of three types of trading agents—rational arbitrageurs, manipulators, and retail momentum followers—based on reinforcement learning, and conducting pilot studies on hourly cryptocurrency data (AAVE, ETC, SUI). The results show that the behavioral characteristics of different agents have differentiated impacts on market stress, liquidity, volatility, and risk-adjusted returns, supporting differentiated regulatory rules for different behavioral types rather than uniform restrictions on volatility or turnover.
AI-generated from reports · 1 days agoUpdated
Coverage timeline
Follow the coverage to understand different sides of the event.
- arXiv q-finAI Agents in Automated Markets
The research team built behavioral models for three types of trading agents—rational arbitrageurs, manipulators, and retail momentum followers—based on reinforcement learning, and conducted a pilot study on hourly cryptocurrency data (AAVE, ETC, SUI). The results show that the behavioral characteristics of different agents have differentiated impacts on market pressure, liquidity, volatility, and risk-adjusted returns. The research conclusions support formulating differentiated regulatory rules for different behavioral types, rather than uniformly restricting volatility or turnover rates.
Trend of this event
Not enough consecutive observations yet; trend is not drawn.