Metraipolis › archive › dc_75bcd263de50

Agent4Crypto: A Dual-Reflective and Market-Feedback-Aligned LLM-Based Multi-Agent System for Cryptocurrency Trading — arXiv:2611.12269

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.12269
License (as archived): CC0-1.0
Archived: 2026-11-10T18:40:12.831Z
SHA-256 of the archived text: ec627c68fa8b406a7802cf7357e216f6e61e2cb9dba572fb75a8f104ca4edf37
Stable URL of this page: https://metraipolis.com/documento/dc_75bcd263de50

How to cite

Agent4Crypto: A Dual-Reflective and Market-Feedback-Aligned LLM-Based Multi-Agent System for Cryptocurrency Trading — arXiv:2611.12269 — arXiv (en), https://arxiv.org/abs/2611.12269 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75bcd263de50 (Metraipolis archive dc_75bcd263de50, sha256 ec627c68fa8b406a7802cf7357e216f6e61e2cb9dba572fb75a8f104ca4edf37)

BibTeX

@misc{dc75bcd263de50,
  title = {Agent4Crypto: A Dual-Reflective and Market-Feedback-Aligned LLM-Based Multi-Agent System for Cryptocurrency Trading — arXiv:2611.12269},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12269},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75bcd263de50; sha256 ec627c68fa8b406a7802cf7357e216f6e61e2cb9dba572fb75a8f104ca4edf37},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12269. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cryptocurrency markets provide a natural testbed for autonomous AI agents because they are digital-native, high-frequency, and machine-speed environments, yet existing methods often struggle with non-stationary market regimes, opaque decisions, and fixed aggregation rules. In this paper, we propose Agent4Crypto, a dual-reflective and market-feedback-aligned multi-agent system. The framework coordinates specialized agents for data collection, analysis, risk assessment, reflection, and trading, synthesizing heterogeneous signals from prices, indicators, news, and charts in an interpretable decision pipeline. Our central design is a trader-centric decision mechanism: three style-specific trader agents, Aggressive, Neutral, and Conservative, generate candidate actions and natural-language rationales from the same market context, while their influence is learned rather than manually fixed. A PPO-based gating policy dynamically allocates trader weights through a dual-reflective feedback process. One reflection stream evaluates post-trade decision quality from realized portfolio outcomes and distills reusable lessons into a Financial ReasoningBank for retrieval in subsequent trader prompts, while the other estimates trader-level counterfactual contribution, indicating which style has recently aligned better with market movements. The PPO state combines Counterfactual Contribution Memory with market features, previous trader weights, and current trader actions, so trader influence adapts across bull, sideways, and bear regimes. Experiments on BTC, ETH, and XRP show that Agent4Crypto improves total return and Sharpe ratio over traditional strategies, machine learning and reinforcement learning baselines, and existing LLM-based trading systems, demonstrating the value of interpretable trader competition and market-feedback-driven adaptation in volatile cryptocurrency markets.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.12269 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-10T18:37:22.455Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).