Explore the corpus

Find evidence, not just documents.

Search Minerva’s current Findings using transparent hybrid retrieval. Results remain strictly inside the configured corpus.

Hybrid retrieval

Results for “financial AI agents”

30 findings

69match

Finding 21611 source

The studys 'minimal information paradigm' forces agents to independently search and verify live data, exposing their current limitations; open-source code and data aim to spur further research, though longer-term evaluations are needed.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

69match

Finding 21591 source

AI-Trader, a new benchmark, tests autonomous agents powered by large language models in live U.S. stocks, A-shares, and cryptocurrency markets, using a fully automated, real-time evaluation system with minimal human input.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

68match

Finding 21601 source

Surprisingly, general intelligence in LLMs does not ensure trading successmost agents failed to generate profits and showed weak risk management, especially in policy-driven markets, highlighting the need for better risk control strategies.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

68match

Finding 21621 source

AI-Trader presents the first live, fully-automated, and data-uncontaminated benchmark for evaluating LLM agents in real-time financial markets across diverse asset classes and granularities. Its minimal information paradigm and autonomous evaluation are highly original, addressing a critical gap. Open-sourced resources and insights into LLM limitations make this work uniquely compelling and impactful.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

67match

Finding 26831 source

BIGFINANCEBENCH is an original, workflow-grounded benchmark evaluating financial-research agents by auditing derivation processes, not just final answers. Its novelty lies in open-ended, multi-source, assumption-dependent tasks and point-weighted rubrics. This compelling approach reveals significant model limitations, driving impactful research in AI, LLMs, and Machine Learning for Investment Management and Trading.

LexicalMeaningQualityGraph

Matched: agents, financial, research, workflow

67match

Finding 26801 source

BIGFINANCEBENCH debuts as a pioneering benchmark, evaluating financial-research AI agents on real-world, auditable workflows with 928 expert-authored questions and a point-weighted rubric, shifting focus from simple Q&A to detailed financial reasoning.

LexicalMeaningQualityGraph

Matched: agents, financial, research, workflow

66match

Finding 29561 source

The Tri-Stage CPA Agent Workflow compresses, analyzes, and allocates news to reduce noise, but the study warns of information overload and notes limitations like focus on long-only ETFs and simplified trading assumptions.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research, workflow

65match

Finding 74371 source

Robust testing with leakage-controlled forward protocols and fixed validation data confirmed STARs genuine research evolution, though the paper leaves open questions about the risks and real-world deployment of autonomous research agents.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

65match

Finding 29571 source

CN-Buzz2Portfolio presents a novel benchmark and dataset for LLM-driven macro and sector asset allocation using Chinese financial news, shifting focus from entity-centric stock picking to market-narrative reasoning. Its Tri-Stage CPA Agent Workflow and rolling-horizon dataset offer unique, impactful tools for evaluating LLMs in emerging market investment management contexts.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research, workflow

65match

Finding 26811 source

Surprisingly, even top AI models scored below 60% on the detailed rubric and under 45% on final-answer accuracy, exposing a significant gap between current AI capabilities and professional financial analysis standards.

LexicalMeaningQualityGraph

Matched: agents, financial, research, workflow

65match

Finding 26821 source

The study reveals most AI errors occur during information retrieval and setup, not calculation, and highlights limitations: tasks are restricted to public-company, English-language scenarios, excluding proprietary databases and live analyst interactions.

LexicalMeaningQualityGraph

Matched: agents, financial, research, workflow

64match

Finding 61201 source

This paper uniquely extends 'nonstandard errors' (NSE) analysis from human researchers to autonomous AI agents, using 150 Claude Code agents on NYSE TAQ SPY data. Its novel three-stage protocol reveals AI analytical diversity and convergence via imitation, offering fresh insights into AI-driven empirical finance, replication credibility, and automated policy evaluation.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

64match

Finding 29541 source

CN-Buzz2Portfolio debuts as a pioneering benchmark and dataset, evaluating how Large Language Models (LLMs) make asset allocation decisions in Chinas financial market using daily trending news for investment signals.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research, workflow

64match

Finding 75351 source

The study reveals LLMs reasoning skills dont guarantee trading success, especially as portfolio size grows, highlighting STOCKBENCHs value for research but exposing current LLM agents limitations in practical trading performance.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

64match

Finding 29551 source

Surprisingly, LLMs excel in trend-driven markets but falter in sideways or low-volatility conditions, sometimes being outperformed by simpler, news-agnostic strategies; bigger models can even underperform smaller ones due to overfitting.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research, workflow

63match

Finding 82201 source

Surprisingly, both adaptive and procedural agents are susceptible but in different ways: adaptive agents overreact to fake news, while procedural agents are easily disrupted by internal memory corruption, highlighting diverse vulnerabilities.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial

63match

Finding 82181 source

A new study reveals that LLM-based autonomous trading agents, now active in real markets, are much more vulnerable to manipulation and system failures than previously believed, raising urgent security concerns.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial

62match

Finding 61181 source

Agents diverged most on which measures to uselike autocorrelation versus variance ratio for market efficiency, or dollar versus share volume for trading activityrather than on trend estimation methods.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

62match

Finding 61191 source

Peer review among AIs barely reduced variation, but showing agents top-rated example papers led to imitation and much narrower results, often by copying methods rather than genuine understanding.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

62match

Finding 61171 source

State-of-the-art AI coding agents analyzing identical NYSE SPY data (2015--2024) produced widely varied results, mainly due to 'nonstandard errors'uncertainty from differing analytical choices, not just human bias.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

61match

Finding 82191 source

Researchers introduce TradeTrap, a novel framework that systematically stress-tests trading agents using real historical data and controlled attacks, exposing how even minor errors can escalate into catastrophic financial lossesrisks missed by standard backtesting.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial

61match

Finding 66151 source

The research demonstrates the potential of LLM-based autonomous agents in quantitative investment, suggesting applications in finance, healthcare, and logistics. Future work will focus on enhancing learning efficiency and real-time adaptation to dynamic environments.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

61match

Finding 82211 source

This paper introduces TradeTrap, a novel, unified framework for systematically stress-testing both adaptive and procedural LLM-based trading agents under adversarial and faulty conditions. Its originality lies in evaluating system-level vulnerabilities across the entire trading pipeline, offering open-source tools and methodology, making it compelling for advancing trustworthy AI-driven financial systems.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial

60match

Finding 58651 source

The study shows that RL agents can enhance portfolio management, with on-policy, actor-critic agents performing best. Future research could explore other RL agents, hyperparameter optimization, and different neural network architectures.

LexicalMeaningQualityGraph

Matched: agents, financial, research

59match

Finding 75361 source

STOCKBENCH introduces a novel, open-source benchmark for evaluating LLM agents in realistic, multi-month stock trading using recent, contamination-free data. Its originality lies in dynamic trading scenarios and rigorous data handling. The compelling finding that LLMs underperform simple baselines highlights significant challenges, making this work highly relevant and impactful for AI-driven finance.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial

58match

Finding 74361 source

STARs self-improving design enabled it to generate significantly higher quality alphas on the CSI300 index (Q1 2026), expand its research vocabulary by 6.9 times, and adopt innovative analytical tools and protocols.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

58match

Finding 75331 source

STOCKBENCH is a new benchmark testing if large language models (LLMs) can autonomously trade stocks profitably, using a contamination-free, continuously updated simulation with real market data and rigorous financial metrics.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial

58match

Finding 74351 source

A new self-tuning agent, STAR, merges a large language model with a metacognitive module to autonomously discover and refine alpha strategies in volatile, noisy financial markets, surpassing traditional human-guided systems.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research

58match

Finding 75341 source

Despite excelling at financial Q&A, most LLMs fail to beat a simple buy-and-hold strategy in real trading scenarios; only models like Kimi-K2 and Qwen3-235B-Ins show notable returns and improved risk management.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial

57match

Finding 74381 source

STAR introduces a self-tuning agent framework coupling an LLM-based alpha researcher with a metacognitive module, uniquely evolving both alpha formulas and research policy. This novel, adaptive approach addresses noisy, non-stationary financial data, offering empirical gains and methodological innovation. Its self-evolving protocols mark a compelling advance in AI-driven quantitative finance.

LexicalMeaningQualityGraph

Matched: agents, autonomous, financial, research