Multi-agent LLM system Agora under Sealed Joint Search conditions produces +1.87 holdout Sharpe on CSI 1000 over a 91-day sealed period, exceeding the best baseline at +1.334 under favorable seed.
Suchow, and Khaldoun Khashanah
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
A closed-loop trading benchmark with a five-axis capability scorecard shows that LLM agents' returns rank poorly against diagnostic measures of their reasoning, with the nominal Sharpe winner exposed as a reliability artifact.
FinCAD mitigates parametric look-ahead bias in LLM financial backtesting via learned adversarial prompts and per-entity-date adaptive CAD penalties, cutting memorised-date returns up to 67% while preserving out-of-sample results and raising in/out-of-sample Spearman correlation from 0.779 to 0.846.
SysTradeBench evaluates 17 LLMs on 12 trading strategies, finding over 91.7% code validity but rapid convergence in iterative fixes and a continued need for human oversight on critical strategies.
InKH architecture absorbs complexity into financial LLM agents, cutting latency 83%, token cost 82%, and stale knowledge 97% while raising task quality 0.108 on a 46k-episode synthetic benchmark versus baselines.
Reported alpha from end-to-end LLM trading agents does not constitute deployment evidence until it passes structural tests for temporal integrity, frictions, robustness, calibration, execution, and disaggregation.
A recursive four-agent trading system cut max drawdown to 9.62% versus ~15% for MVO and FinBERT across five geopolitical stress events, while earning near-zero returns in a 2023–2025 bull market.
Reproducibility audit of 30 LLM trading papers shows execution assumptions under-reported relative to agent architectures, illustrated by a 10-equity example where frictions compress returns.
citing papers explorer
-
AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolution
Multi-agent LLM system Agora under Sealed Joint Search conditions produces +1.87 holdout Sharpe on CSI 1000 over a 91-day sealed period, exceeding the best baseline at +1.334 under favorable seed.
-
CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents
A closed-loop trading benchmark with a five-axis capability scorecard shows that LLM agents' returns rank poorly against diagnostic measures of their reasoning, with the nominal Sharpe winner exposed as a reliability artifact.
-
Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models
FinCAD mitigates parametric look-ahead bias in LLM financial backtesting via learned adversarial prompts and per-entity-date adaptive CAD penalties, cutting memorised-date returns up to 67% while preserving out-of-sample results and raising in/out-of-sample Spearman correlation from 0.779 to 0.846.
-
SysTradeBench: An Iterative Build-Test-Patch Benchmark for Strategy-to-Code Trading Systems with Drift-Aware Diagnostics
SysTradeBench evaluates 17 LLMs on 12 trading strategies, finding over 91.7% code validity but rapid convergence in iterative fixes and a continued need for human oversight on critical strategies.
-
Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents
InKH architecture absorbs complexity into financial LLM agents, cutting latency 83%, token cost 82%, and stale knowledge 97% while raising task quality 0.108 on a 46k-episode synthetic benchmark versus baselines.
-
The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence
Reported alpha from end-to-end LLM trading agents does not constitute deployment evidence until it passes structural tests for temporal integrity, frictions, robustness, calibration, execution, and disaggregation.
-
Recursive Multi-Agent Trading System: Iterative Optimized Portfolio Strategy Under Geopolitical Uncertainty
A recursive four-agent trading system cut max drawdown to 9.62% versus ~15% for MVO and FinBERT across five geopolitical stress events, while earning near-zero returns in a 2023–2025 bull market.
-
Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems
Reproducibility audit of 30 LLM trading papers shows execution assumptions under-reported relative to agent architectures, illustrated by a 10-equity example where frictions compress returns.