{"paper_id":"2510.19173","title":"News-Aware Direct Reinforcement Trading for Financial Markets","authors":["Qing-Yu Lan","Zhan-He Wang","Jun-Qian Jiang","Yu-Tong Wang","Yun-Song Piao"],"paper_date":"2025-10-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.19173v1","page_url":"https://thequant.space/flowcharts/news-aware-direct-reinforcement-trading-for-financial-market/","scores":{"empirical_rigor":4,"math_complexity":6.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a news-aware reinforcement learning framework that directly uses LLM-derived news sentiment scores together with raw price and volume data as inputs processed by sequence models for end‑to‑end trading decisions.","quote":"In this work, we directly use the news sentiment scores derived from large language models, together with raw price and volume data, as observable inputs for reinforcement learning.","summary":"The financial market is known to be highly sensitive to news. Therefore, effectively incorporating news data into quantitative trading remains an important challenge. Existing approaches typically rely on manually designed rules and/or handcrafted features. In this work, we directly use the news…","strategy":"news-aware RL framework with LSTM"},"assumptions":{"status":"available","items":[{"assumption":"Leaving out news makes the market only partially observable and increases non‑stationarity.","type":"market","stated":"implied","quote":"Leaving out news makes the whole market condition only partially observable and increases non-stationarity."},{"assumption":"The dataset split chronologically (70% train, 15% validation, 15% test) prevents look‑ahead bias and yields realistic performance evaluation.","type":"data","stated":"explicit","quote":"We divided the whole dataset into training, validation and test area using a chronological split to prevent look-ahead bias and ensure realistic performance evaluation"},{"assumption":"1‑minute OHLCV data from Binance for BTC/USDT and news scraped from Yahoo Finance are sufficient to represent the cryptocurrency market and its news flow.","type":"data","stated":"implied","quote":"The whole dataset, including market 1-minute OHLCV (i.e. open, high, low, close, volume) time-series sourced from Binance Exchange"},{"assumption":"Sequence‑based agents (LSTM, Transformer) can capture temporal dependencies better than MLP agents.","type":"model","stated":"explicit","quote":"confirming the value of modeling prices and sentiment signals as continuous time-series rather than isolated inputs"}]},"datasets":{"status":"available","items":[{"name":"Binance BTC/USDT 1‑minute OHLCV","provider":"Binance Exchange","kind":"market-prices","access":"public","period":"2019-12-31 00:00:00 to 2024-01-24 21:48:","universe":"BTC/USDT","quote":"The whole dataset, including market 1-minute OHLCV (i.e. open, high, low, close, volume) time-series sourced from Binance Exchange","known_id":"binance"},{"name":"Yahoo Finance Bitcoin news","provider":"Yahoo Finance","kind":"text-news","access":"public","period":"2019-12-31 00:00:00 to 2024-01-24 21:48:","universe":"Bitcoin‑related news","quote":"news text scrapped from Yahoo Finance related to Bitcoin","known_id":"yahoo-finance"}],"known":[{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"Dataset Preprocessing The whole dataset, including market 1-minute OHLCV (i.e. open, high, low, close, volume) time-series sourced from Binance Exchange1 for BTC/USDT and news text scrapped from Yahoo Finance related to Bitcoin2.","mentions":1,"used_in":1},{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"Dataset Preprocessing The whole dataset, including market 1-minute OHLCV (i.e. open, high, low, close, volume) time-series sourced from Binance Exchange1 for BTC/USDT and news text scrapped from Yahoo Finance related to Bitcoin2.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":"BTC/USDT","asset_class":"crypto","frequency":"intraday"},"data_resolution":"intraday-bars"},"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":"Incorporating LLM‑derived news‑sentiment inputs yields higher returns than the corresponding model without LLM signals, confirming the value of news analysis.","kind":"performance","quote":"Incorporating LLM-derived news-sentiment inputs yields higher returns than the corresponding model without LLM signals, confirming the value of news analysis."},{"finding":"The proposed framework exceeds BTC market benchmarks, with LSTM‑based agents achieving up to 124.5% top‑1 return for DDQN, outperforming both MLP agents and models without news signals.","kind":"performance","quote":"results illustrate that our proposed framework can exceed the BTC market benchmarks."}],"reported_performance":{"strategy":"news-aware RL framework with LSTM","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":124.5,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":13,"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":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":"2026-11-14T16:38:33Z"},"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/"}