{"paper_id":"2508.11152","title":"AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions","authors":["Tianjiao Zhao","Jingrao Lyu","Stokes Jones","Harrison Garber","Stefano Pasquali","Dhagash Mehta"],"paper_date":"2025-08-15","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2508.11152v1","page_url":"https://thequant.space/flowcharts/alphaagents-large-language-model-based-multi-agents-for-equ/","scores":{"empirical_rigor":6,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a novel multi‑agent investment framework that uses LLM‑powered collaboration and debate to collect and synthesize equity research inputs.","quote":"In this work, we propose a novel multi-agent investment framework that leverages LLM-powered collaboration and debate to collect and synthesize equity research inputs.","summary":"The field of artificial intelligence (AI) agents is evolving rapidly, driven by the capabilities of Large Language Models (LLMs) to autonomously perform and refine tasks with human-like efficiency and adaptability. In this context, multi-agent collaboration has emerged as a promising approach…","strategy":"AlphaAgents multi-agent portfolio"},"assumptions":{"status":"available","items":[{"assumption":"Each agent only accesses data relevant to its specific role and assigned task.","type":"data","stated":"explicit","quote":"Each agent is granted access only to the data relevant to its specific role and assigned task."},{"assumption":"Risk‑averse and risk‑neutral agent behavior is modeled via prompt engineering that embeds investor traits into agent instructions.","type":"model","stated":"explicit","quote":"We design agents for both risk‑averse and risk‑neutral scenarios using prompt engineering to embed investor traits directly into agent instructions."}]},"datasets":{"status":"available","items":[{"name":"10‑K and 10‑Q financial disclosures","provider":null,"kind":"fundamentals","access":"public","period":null,"universe":null,"quote":"10K/10Q Fundamental Agent Financial disclosure data (includes discussion of major company prospectus and financial statements)."},{"name":"Bloomberg financial news","provider":"Bloomberg","kind":"text-news","access":"commercial","period":null,"universe":null,"quote":"Bloomberg ID Sentiment Agent Ticker’s corresponding unique identifier for Bloomberg News","known_id":"bloomberg"},{"name":"Historical stock price and volume data","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":null,"universe":null,"quote":"Price (Open, High, Low, Close) Valuation Agent The initial, highest, lowest, and final trading price of a stock within a specific trading period","known_id":"yahoo-finance"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"The primary data sources utilized in the system are listed in Table 1, including 10-K and 10-Q financial disclosures, Bloomberg financial news, and historical stock price and volume data from Yahoo Finance.","mentions":3,"used_in":1},{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The primary data sources utilized in the system are listed in Table 1, including 10-K and 10-Q financial disclosures, Bloomberg financial news, and historical stock price and volume data from Yahoo Finance.","mentions":2,"used_in":1}],"sample":{"start":"2024-02","end":"2024-06","market":null,"asset_class":"equities","frequency":null},"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":"In the risk‑neutral setting, the multi‑agent framework outperforms both the benchmark and single‑agent frameworks during the testing window.","kind":"performance","quote":"In the risk-neutral setting, the proposed multi-agent outperforms the benchmark as well as the single agent framework during the testing window."},{"finding":"In the risk‑averse setting, all agent‑selected portfolios underperform the benchmark, partly due to exclusion of volatile technology stocks.","kind":"performance","quote":"In the risk-averse setting, all agent-selected portfolios followed a conservative investment strategy, leading to underperformance relative to the benchmark."},{"finding":"The multi‑agent portfolio shows slightly lower volatility and reduced drawdowns compared to individual valuation and fundamental portfolios.","kind":"performance","quote":"the multi-agent portfolio exhibited slightly lower volatility and reduced drawdowns, indicating an ability to mitigate losses more effectively than the individual strategies."}],"reported_performance":{"strategy":"AlphaAgents multi-agent portfolio","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"citations":{"cited_by_in_corpus":8,"by_independent_authors":7,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":6,"unclassified":2},"independent_papers":[],"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":"2026-11-14T17:29:44Z"},"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/"}