EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
Source
Sehee Kim, Yumin Choi, Minki Kang, Sung Ju Hwang
Author
Sehee Kim, Yumin Choi, Minki Kang, Sung Ju Hwang
Date
Key takeaways · AI-distilled
The backbone LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → stays completely fixed in EvolveTrade — only the system-prompt policy is rewritten, by a separate Policy AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → using accumulated decision traces and realized portfolio outcomes, so the adaptation happens entirely in text rather than model weights.
Behavioral analysis shows self-evolved policies increase code-mediated analysis and activate more regime-relevant computations — the agent doesn't just get better returns, it changes how it reasons depending on market conditions.
The authors trace case-level policy-to-return attributions, identifying specific policy-induced allocation changes that produced measurable return differences, rather than reporting only aggregate performance.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
system prompt — The standing instructions a model receives before any user input — defining its role, rules, tools, and tone for the whole conversation.
Why it matters
Demonstrates a concrete self-evolution technique, refining the system promptThe standing instructions a model receives before any user input — defining its role, rules, tools, and tone for the whole conversation.Full definition → as an updatable policy from outcome feedback, that generalizes beyond trading to any tool-using agent needing to adapt strategy without retraining.
articleSelf-Evolving Embodied Agents via Skill-Harness EvolutionPeidong Wang, Zhiming Ma, Ying Chang, Xufang Luo, Xiaocui Yang, Shi Feng, Yuqing Yang, Dongsheng Li
articleBacktrader-Bench: Benchmarking LLM Agents on Algorithmic Trading with Self-Generated MCQsRuoxi Zhao, Maziar Raissi
articleWhy Better Models Can Create Riskier Systems: Evidence from LLM Agents in Financial MarketsJillian Ross, Eric So, Zoe De Simone, Charles Pozniak, Andrew W. Lo