{"paper_id":"2510.15949","title":"ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination","authors":["Charidimos Papadakis","Angeliki Dimitriou","Giorgos Filandrianos","Maria Lymperaiou","Konstantinos Thomas","Giorgos Stamou"],"paper_date":"2025-10-10","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.15949v2","page_url":"https://thequant.space/flowcharts/atlas-adaptive-trading-with-llm-agents-through-dynamic-prom/","scores":{"empirical_rigor":6,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes ATLAS, a multi‑agent framework for LLM‑based stock market decision‑making, and introduces Adaptive‑OPRO, a prompt‑optimization mechanism for sequential trading.","quote":"we propose ATLAS, a multi‑agent framework that provides a foundational structure for experimentation in LLM‑based stock market decision‑making; (ii) we introduce Adaptive‑OPRO, a prompt optimization mechanism for sequential settings that supports behavioral adaptation through ongoing market interaction","summary":"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…","strategy":"ATLAS Adaptive-OPRO"},"assumptions":{"status":"available","items":[{"assumption":"Agents make daily end‑of‑day decisions and receive delayed, noisy feedback.","type":"model","stated":"implied","quote":"End‑of‑day decisions provide stable feedback for optimization under delayed, noisy outcomes, but prevent agents from reacting to intraday moves"},{"assumption":"The order‑level simulator abstracts away market microstructure such as slippage, partial fills, latency, and intraday dynamics.","type":"execution","stated":"explicit","quote":"Agents operate in an order‑level simulator that enforces trading semantics while abstracting market microstructure: slippage, partial fills, latency, and intraday dynamics are not modeled"},{"assumption":"Experiments are limited to three liquid equities over two‑month, regime‑specific windows.","type":"market","stated":"explicit","quote":"we focus on three liquid equities over two‑month, regime‑specific windows with daily decisions to reduce confounding from asset heterogeneity and shifting market structure"},{"assumption":"Each configuration is run three times due to resource constraints, limiting statistical power.","type":"statistical","stated":"explicit","quote":"Each configuration runs three times due to resource constraints, capturing stochastic variance but limiting statistical power"},{"assumption":"Results are interpreted as behavioral evidence about Adaptive‑OPRO rather than market‑wide performance claims.","type":"other","stated":"explicit","quote":"Results should be read as behavioral evidence about Adaptive‑OPRO, not as market‑wide performance claims"}]},"datasets":{"status":"available","items":[{"name":"Massive API","provider":null,"kind":"text-news","access":"unknown","period":null,"universe":null,"quote":"as batches of timestamped items containing title, URL, summary, and keywords"}],"known":[],"sample":{"start":null,"end":null,"market":"equities","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":"Agents operate in an order‑level simulator that enforces trading semantics while abstracting market microstructure: slippage, partial fills, latency, and intraday dynamics are not modeled","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"Agents operate in an order‑level simulator that enforces trading semantics while abstracting market microstructure: slippage, partial fills, latency, and intraday dynamics are not modeled","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Adaptive‑OPRO consistently outperforms fixed prompts across multiple market regimes and LLM families.","kind":"performance","quote":"Across regime‑specific equity studies and multiple LLM families, Adaptive‑OPRO consistently outperforms fixed prompts"},{"finding":"Reflection‑based feedback fails to provide systematic gains and can be inconsistent across models.","kind":"negative","quote":"while standard reflection proves inconsistent"},{"finding":"Additional input modalities (e.g., news, fundamentals) are not uniformly beneficial and depend critically on market conditions.","kind":"performance","quote":"additional input modalities are not uniformly beneficial and depend critically on market conditions"},{"finding":"Adaptive‑OPRO improves risk‑adjusted metrics such as Sharpe Ratio, Sortino Ratio, ROIC, and profit per trade compared to baselines and reflection.","kind":"performance","quote":"Adaptive‑OPRO reduces these gaps, yet reflection often increases variance without clear risk‑adjusted gains"},{"finding":"Reflection can degrade performance, as shown in a case where it caused re‑entry into a weak market leading to a loss.","kind":"negative","quote":"free‑form reflection can degrade performance by injecting prescriptive guidance that the agent follows even when market conditions do not justify action"}],"reported_performance":{"strategy":"ATLAS Adaptive-OPRO","sharpe":6.63,"sharpe_benchmark":null,"annual_return_pct":-6.16,"total_return_pct":null,"max_drawdown_pct":14.05},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[{"paper":{"paper_id":"2510.08068","title":"An Adaptive Multi Agent Bitcoin Trading System","paper_date":"2025-10-09","authors":["Aadi Singhi"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/an-adaptive-multi-agent-bitcoin-trading-system/"},"question":"Does providing feedback to adaptive multi‑agent trading systems improve performance?","this_paper_finding":"Reflection‑based feedback fails to provide systematic gains and can be inconsistent across models.","other_paper_finding":"Adding weekly verbal feedback improved total performance by 31% and reduced bearish losses by 10%.","other_paper_quote":"Adding weekly feedback further improved total performance by 31% and reduced bearish losses by 10%","note":"A shows +31% total performance and -10% bearish losses with weekly verbal feedback; B finds reflection‑based feedback gives no systematic gains and is inconsistent across models.","confidence":0.628}],"qualifies":[],"compared_with":48,"citations":{"cited_by_in_corpus":3,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":2,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2602.07085","title":"QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining","paper_date":"2026-02-06","authors":["Jun Han","Shuo Zhang","Wei Li","Zhi Yang","Yifan Dong","Tu Hu"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/quantaalpha-an-evolutionary-framework-for-llm-driven-alpha-mining/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2604.17327","title":"Signal or Noise in Multi-Agent LLM-based Stock Recommendations?","paper_date":"2026-04-19","authors":["George Fatouros","Kostas Metaxas"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/signal-or-noise-in-multi-agent-llm-based-stock-recommendations/"},"how":"uses_method_or_data","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T16:38:35Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}