{"paper_id":"2511.13614","title":"Market-Dependent Communication in Multi-Agent Alpha Generation","authors":["Jerick Shi","Burton Hollifield"],"paper_date":"2025-11-17","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2511.13614v1","page_url":"https://thequant.space/flowcharts/market-dependent-communication-in-multi-agent-alpha-generati/","scores":{"empirical_rigor":6,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper empirically demonstrates that optimal communication structures for multi‑agent LLM trading depend on market volatility, and that all structures converge to similar strategy correlations.","quote":"Our contributions are: • Market-dependent communication effectiveness: Large-scale empirical demonstration that optimal communication structure varies systematically with market volatility and correlation characteristics, with competitive conversation excelling in volatile markets and collaborative conversation dominat","summary":"Multi-strategy hedge funds face a fundamental organizational choice: should analysts generating trading strategies communicate, and if so, how? We investigate this using 5-agent LLM-based trading systems across 450 experiments spanning 21 months, comparing five organizational structures from…","strategy":"LLM-based multi-agent trading with communication structures"},"assumptions":{"status":"available","items":[{"assumption":"Daily OHLCV data from Yahoo Finance are accurate and sufficient for alpha evaluation.","type":"data","stated":"implied","quote":"We retrieve daily OHLCV data from Yahoo Finance for January 1, 2024 to September 30, 2025 (21 months) with monthly rebalancing."}]},"datasets":{"status":"available","items":[{"name":"Yahoo Finance daily OHLCV","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2024-01-01 to 2025-09-30","universe":"General Universe: SPY, JNJ, JPM, WMT, XOM, PG, UNH, HD, VZ, KO","quote":"We retrieve daily OHLCV data from Yahoo Finance for January 1, 2024 to September 30, 2025 (21 months) with monthly rebalancing.","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"A.2 Market Data and Universe Construction We test three universes designed to span volatility and correlation characteristics: • General Universe: SPY, JNJ, JPM, WMT, XOM, PG, UNH, HD, VZ, KO • Technology Universe: NVDA, MSFT, GOOGL, AAPL, META, AMZN, TSLA, AMD, INTC, ORCL • Finance Universe: JPM, BAC, WFC, GS, MS, C, BLK, SPGI, AXP, USB We retrieve daily OHLCV data from Yahoo Finance for January 1, 2024 to September","mentions":1,"used_in":1}],"sample":{"start":"2024-01","end":"2025-09","market":"US stocks (technology, general, finance universes)","asset_class":"equities","frequency":"monthly"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Communication improves performance, with competitive conversation excelling in volatile technology stocks and collaborative conversation dominating stable general stocks; finance stocks show no benefit.","kind":"performance","quote":"Communication improves performance in multi-agent trading systems, but optimal design depends on market characteristics. Competitive conversation excels in volatile technology stocks, while collaborative conversation dominates stable general stocks. Finance stocks resist all interventions."},{"finding":"All organizational structures converge to similar strategy correlations regardless of information sharing, eliminating diversity loss.","kind":"theoretical","quote":"All organizational structures converge to similar strategy correlations regardless of information sharing, eliminating \"diversity loss\" as communication’s primary failure mode."},{"finding":"Conversation quality scores have zero correlation with returns; finance shows highest quality yet minimal performance, while tech shows strong returns with lowest scores.","kind":"statistical","quote":"Conversation quality scores show zero correlation with returns: finance exhibits highest quality yet minimal performance, while tech achieves strong returns with lowest scores."},{"finding":"Competitive agents focus on tactical positioning while collaborative agents develop methodological sophistication.","kind":"other","quote":"competitive agents focus on tactical positioning while collaborative agents develop methodological sophistication."},{"finding":"CORE (conversation quality) change is negatively correlated with performance improvement (r = -0.54).","kind":"statistical","quote":"Correlation between CORE change and performance improvement yields r = -0.54."}],"reported_performance":{"strategy":"LLM-based multi-agent trading with communication structures","sharpe":2.47,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[{"paper":{"paper_id":"2307.11846","title":"Social and individual learning in the Minority Game","paper_date":"2023-07-21","authors":["Bryce Morsky","Fuwei Zhuang","Zuojun Zhou"],"empirical_rigor":2,"page_url":"https://thequant.space/flowcharts/social-and-individual-learning-in-the-minority-game/"},"question":"Does information sharing affect strategy diversity in multi‑agent market games?","this_paper_finding":"All organizational structures converge to similar strategy correlations regardless of information sharing, eliminating diversity loss.","other_paper_finding":"Social learning causes a crash in strategy‑table diversity, potentially locking the population into a maximally inefficient state.","other_paper_quote":"This phe-nomenon occurs because there is a crash in strategy table diversity as agents lose strategy tables 5 (a) No social or individual learning, N = 1001 (b) Only individual learning, N = 1001 (c) Only social learning, N = 1001 (d) Individual and social learning, N = 1001 (e) Only social learning, N = 101 Figure 1: Time series of the attendance A for no individual or social learning (a), only individual learn-ing","note":"A reports a crash in diversity due to social learning, while B reports no diversity loss as all structures converge, contradicting A.","confidence":0.499}],"qualifies":[],"compared_with":28,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/Jerick-1380/multi-agent-alpha-generation","note":null},"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":"2026-11-14T17:21:37Z"},"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/"}