mlsanityData to 7 Oct 2026

ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism

arXiv 2508.00554 ↗First posted 1 Aug 2025q-fin.TR cs.CL q-fin.CPcited by 8

On the map: LLM agents and tool use → Financial trading and forecasting agents

Abstract (arXiv)

In financial trading, large language model (LLM)-based agents demonstrate significant potential, but their decisions can be sensitive to noisy and non-stationary market information. We propose ContestTrade, a multi-agent trading system with an internal competitive mechanism inspired by institutional investment workflows. The system consists of two specialized teams: (1) a Data Team that processes and condenses massive market data into diversified textual factors optimized for constrained LLM context windows, and (2) a Research Team that produces parallelized multipath trading decisions via tool-augmented deep research. The core design is a "Quantify-Predict-Allocate" contest mechanism within each team: agent outputs are scored only after market outcomes become observable, future utility is predicted from historical scores, and resources are allocated to agents with positive predicted utility. In a post-2024 A-share backtest, ContestTrade achieves higher backtested return and risk-adjusted performance than the evaluated baselines. We further describe the temporal protocol, implementation choices, and limitations to clarify the scope of these results.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 21 of its 35 references that are in the map. First posted on arXiv 1 Aug 2025.

Builds on

21 of 35 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025MASS: Muli-agent simulation scaling for portfolio construction15 May
  2. 2024TradingAgents: Multi-Agents LLM Financial Trading Framework28 Dec
  3. 2024Large Language Model Agent in Financial Trading: A Survey26 Jul
  4. 2024FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making9 Jul
  5. 2024FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models23 May
  6. 2023FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design23 Nov

Other references · 15

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2023BloombergGPT: A Large Language Model for Financecited by 923
  5. 2023FinGPT: Open-Source Financial Large Language Modelscited by 244
  6. 2024A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalistcited by 137
  7. 2023Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Modelscited by 125
  8. 2025NoLiMa: Long-Context Evaluation Beyond Literal Matchingcited by 120
  9. 2023Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investmentcited by 54
  10. 2024Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Modelscited by 35
  11. 2024LLMFactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Predictioncited by 31
  12. 2024QuantAgent: Seeking Holy Grail in Trading by Self-Improving Large Language Modelcited by 30
3 more
  1. 2024Can Large Language Models Beat Wall Street? Unveiling the Potential of AI in Stock Selectioncited by 29
  2. 2023Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements?cited by 15
  3. 2024Alpha-GPT 2.0: Human-in-the-Loop AI for Quantitative Investmentcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2026Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks
  2. 2025When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents
  3. 2025Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents
  4. 2025TradingGroup: A Multi-Agent Trading System with Self-Reflection and Data-Synthesis
  5. 2025ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination
  6. 2026AlphaCrafter: Harnessing Multi-Agent Workflows for Cross-Sectional Quantitative Trading
  7. 2026Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness
  8. 2026PolySwarm: A Multi-Agent Large Language Model Framework for Prediction Market Trading and Latency Arbitrage