arXiv cs.MA· Russlan Ramdowar·· 11 小时前AI 评分26
有限的 AI 研究预算该花在哪：价格更新、深度预测刷新还是精选股编辑复核？
When Is Fresh AI Stock Analysis Worth It? Allocating a Limited Research Budget Across Price Updates, Deep Forecast Refreshes, and Editorial Reviews of Top Stock Picks
AI 导读
一项基于 8,120 份 iPulse AI 报告（消耗近 1 亿输出与推理 token、覆盖 203 只股票）的研究比较了重新定价旧目标、机械重置增长路径与全新多智能体报告三种研究投入方式。
正文 · 原文
Abstract:When is another AI research run worth more than keeping that money invested? Using 8,120 iPulse AI reports that consumed nearly 100 million output and reasoning tokens on the same 203 stocks across four production batches, we compare repricing old targets (with and without shock safeguards), mechanical growth-path resets and fresh multi-agent reports. Ten matched configurations represent seven investment frameworks.
The primary economic test selects equal-weight Top 10 USD portfolios from one-year forecasts, net of 10 bps trading costs and a USD 3,000 all-in charge for fresh research on a USD 300,000 account. In two unchanged-model short windows, guarded reuse averages 2.25%, versus 1.66% for SPY and 4.24% for fresh reports. Guarded reuse beats SPY in all three short windows. Extending the first holding window to 176 days reverses the comparison: guarded reuse returns -11.26%, fresh reports +8.55%, and SPY +3.46%, motivating the thesis half-life question.
Supporting quarter-forecast diagnostics show that mechanically resetting old growth paths closes 98% of the MAE gap to fresh reports, yet Fresh and Reset share only 1-4 Top 10 stocks. Top 30 reverses the unchanged-model comparison in favor of guarded reuse (4.17% versus 1.37%). Concentration tests expose dependence on exceptional winners. Nine editorial editions show substantial between-edition turnover, but each final screen retains its own incoming list.
Recurring budget scenarios retain initial holdings: monthly costs approach realized short-window refresh value, while weekly budgets require larger additional gains. A matched ranking-continuity extension extracts further value from retained forecasts without eliminating thesis ageing. The architecture separates continuous price monitoring, episodic thesis rebuilding and evidence-based editorial checks.
| Comments: | 28 pages, 9 figures. Version 2.1.0: revised operating budgets and token provenance; added matched ranking-continuity experiment. Paper and artifacts: this https URL . Code: this https URL |
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.04348 [cs.MA] |
| (or arXiv:2611.04348v2 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2611.04348 arXiv-issued DOI via DataCite |
Submission history
From: Russlan Ramdowar [view email]
[v1]
Tue, 3 Nov 2026 05:30:18 UTC (153 KB)
[v2]
Wed, 4 Nov 2026 09:08:37 UTC (159 KB)
来源：arXiv cs.MA · arxiv.org