The study examines whether large language models (LLMs) can accurately simulate individual financial users by conducting a longitudinal paper‑trading experiment with 80 participants. Using a rolling next‑day prediction protocol, the researchers compared LLM predictions to a simple recent‑activity persistence baseline across multiple behavioral fidelity levels, from trade occurrence to asset selection and portfolio outcomes. Results show that no LLM consistently outperforms the baseline, with fidelity decreasing at finer behavioral granularity, and that recent trading history largely drives activity predictions while asset selection depends more on available evidence.
By Jiajie He, Jiangyuan Hong, Xintong Chen, Dongling Ni, Wenjin Liu
arXiv:2608. 04095v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used as personalized assistants in high-stakes domains such as financial advising, yet it remains unclear whether they can maintain and update an individualized user model over long horizons.
By Ben Wang, Kang Zhou, Lifan Guo, Feng Chen, Chi Zhang
arXiv:2606. 31522v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous financial agents initialized with explicit behavioral mandates such as "preserve capital" or "avoid speculative bets" that are meant to govern every decision throughout deployment.
By Muhammad Usman Safder (Steve), Ayesha Gull (Steve), Rania Elbadry (Steve), Fan Zhang (Steve), Yankai Chen (Steve), Xueqing Peng (Steve), Xue (Steve), Liu, Preslav Nakov, Zhuohan Xie
META (Memory Enhanced Trading Agent) is a new agent-based trading framework that augments large language models with episodic memory. It combines specialized indicator agents—such as Trend, MACD, Stochastic, RSI, SMA, AVWAP, and Heikin‑Ashi—with a Decision Agent that fuses their reports, while a Memory module retrieves and updates past trading episodes encoded as market state embeddings with outcomes and reflections. By recalling relevant experiences and adaptively reweighting signals under similar market regimes, META improves directional accuracy and robustness in short‑horizon evaluations, offering regime‑aware, interpretable, and low‑latency decision‑making for financial trading.
By Nuoyue Xu, Jiang Liu, Wenxuan Huang, Xiang Zhang, Juntai Cao, Jiaqi Wei
Large language models (LLMs) are being tested as simulators of individual financial decision-making. In a controlled paper‑trading experiment with 120 volunteers, the study evaluated whether an LLM could predict a participant’s next‑day trading action, chosen security, and transaction size using only pre‑cutoff information. Results showed that including market context improved predictions of actions and tickers, but sizing remained challenging, and the models tended to over‑predict hold actions, under‑predict sells, and simplify multi‑security trades.
By Jiajie He, Jiangyuan Hong, Dongling Ni, Wenjin Liu, Xintong Chen
arXiv:2407. 18957v5 Announce Type: replace-cross Abstract: Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.
By Chong Zhang, Xinyi Liu, Zhongmou Zhang, Mingyu Jin, Lingyao Li, Zhenting Wang, Wenyue Hua, Dong Shu, Suiyuan Zhu, Xiaobo Jin, Sujian Li, Mengnan Du, Yongfeng Zhang
arXiv:2608.22852v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific inv...
By Sahong Park, Suhwan Park, Hoyoung Lee, Gakyung Kwon, Wonbin Ahn, Jaewon Choi, Alejandro Lopez-Lira, Yoon Kim, Chanyeol Choi, Hyeongwoo Kong, Yongjae Lee
arXiv:2609.07675v1 Announce Type: cross
Abstract: Transaction-local controls answer whether one financial request may proceed, but market behavior can be distributed across messages, agents, assets,...
By Zelin Li, Yiyun Su, Matt White, Zhipeng Wang, Xiao-Yang Liu, Tianyu Shi
arXiv:2610.18602v1 Announce Type: new
Abstract: Point-in-time (PIT) agents can recall post-cutoff facts even when their external evidence respects a historical cutoff. We examine whether this access...
By Rongtian Ye
The paper introduces Steward, a multi‑agent LLM system for autonomous investing that uses a type system to limit self‑evolution. It employs nine role‑specialised agents—four analysts, a Portfolio Manager, a Risk Manager, and a shared memory layer—to process news, SEC filings, macro data, and market feeds, while a reflector and deterministic gate enable reversible learning from trade outcomes. In a five‑month live deployment, Steward achieved a 0.3% loss after a 24.6% sector drawdown, and backtests show its invariant core consistently reduces maximum drawdown across random entry policies.
By Yebo Feng, Jingyang Dai, Liangrui Pan, Nelson Lau, Jiahua Xu, Yang Liu
EvolveTrade is a self‑evolving framework that treats the system prompt of a tool‑using LLM trading agent as a text‑parameterized policy. After each update interval, a Policy Agent revises this policy using accumulated decision traces and portfolio feedback while keeping the backbone LLM fixed, allowing the agent to refine its information‑acquisition and portfolio‑construction procedures over time. Experiments across multiple market regimes and two LLM backbones show that EvolveTrade often improves Sharpe Ratio and Cumulative Return over fixed‑policy baselines, with behavioral analyses indicating increased code‑mediated analysis and regime‑relevant computations.
By Sehee Kim, Yumin Choi, Minki Kang, Sung Ju Hwang
The paper investigates how the age of financial news affects portfolio decisions by comparing reinforcement learning (RL) policies that incorporate timing information with large language model (LLM) approaches that either retain or filter out older news signals. Using an LLM to extract signals from SEC disclosures, the study finds that RL models can respond to timing cues in controlled tests, yet historical returns show no consistent advantage from including such information. In contrast, filtering out older news in the LLM approach yields the highest average net return, achieving 18.43% per year when news delivery is delayed by four weeks, outperforming all RL strategies that used news.
By Bolin Song (Cornell University), Surui Xiang (United Nations)