# ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination

arXiv: https://arxiv.org/abs/2510.15949 · HTML: https://mlsanity.com/paper/2510.15949/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 44 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 12 of 12)

- [EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers](https://mlsanity.com/paper/2309.08532/) (2023)
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design](https://mlsanity.com/paper/2311.13743/) (2023)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (2024)
- [Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies](https://mlsanity.com/paper/2502.02533/) (2025)
- [Non-Determinism of "Deterministic" LLM Settings](https://mlsanity.com/paper/2408.04667/) (2024)
- [FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading](https://mlsanity.com/paper/2502.11433/) (2025)
- [Walking a Tightrope -- Evaluating Large Language Models in High-Risk Domains](https://mlsanity.com/paper/2311.14966/) (2023)
- [TradExpert: Revolutionizing Trading with Mixture of Expert LLMs](https://mlsanity.com/paper/2411.00782/) (2024)
- [StockSim: A Dual-Mode Order-Level Simulator for Evaluating Multi-Agent LLMs in Financial Markets](https://mlsanity.com/paper/2507.09255/) (2025)
- [GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering](https://mlsanity.com/paper/2407.12865/) (2024)
- [Large Language Models Prompting With Episodic Memory](https://mlsanity.com/paper/2408.07465/) (2024)

## Built on by (most cited first, 7 of 7)

- [QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining](https://mlsanity.com/paper/2602.07085/) (2026)
- [SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents](https://mlsanity.com/paper/2605.06822/) (2026)
- [Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence](https://mlsanity.com/paper/2608.21156/) (2026)
- [Signal or Noise in Multi-Agent LLM-based Stock Recommendations?](https://mlsanity.com/paper/2604.17327/) (2026)
- [LLM Agents for Time-Series: A Survey](https://mlsanity.com/paper/2608.26226/) (2026)
- [EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents](https://mlsanity.com/paper/2609.17632/) (2026)
- [AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search](https://mlsanity.com/paper/2608.11250/) (2026)

## Abstract (arXiv)

Large language models show promise for financial decision-making, yet deploying them as autonomous trading agents raises fundamental challenges: how to adapt instructions when rewards arrive late and obscured by market noise, how to synthesize heterogeneous information streams into coherent decisions, and how to bridge the gap between model outputs and executable market actions. We present ATLAS (Adaptive Trading with LLM AgentS), a unified multi-agent framework that integrates structured information from markets, news, and corporate fundamentals to support robust trading decisions. Within ATLAS, the central trading agent operates in an order-aware action space, ensuring that outputs correspond to executable market orders rather than abstract signals. The agent can incorporate feedback while trading using Adaptive-OPRO, a novel prompt-optimization technique that dynamically adapts the prompt by incorporating real-time, stochastic feedback, leading to increasing performance over time. Across regime-specific equity studies and multiple LLM families, Adaptive-OPRO consistently outperforms fixed prompts, while reflection-based feedback fails to provide systematic gains.