Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors

arXiv:2609.27051 · cs.AI, q-fin.PM, q-fin.ST · Submitted 2026-09-22 · Read on arXiv

cs.AI, q-fin.PM, q-fin.ST

Submitted: 2026-09-22

Updated: 2026-09-22

Terminology

• alpha — 12× in this paper · explained in 1 episode
• Regret — 8× in this paper · explained in 3 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Agentic Loop — 3× in this paper · explained in 1 episode
• Calibration — 3× in this paper · explained in 7 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Allocator — 2× in this paper · explained in 1 episode
• Self-Evolving Agents — 2× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Admissibility — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Alpha Decay — 1× in this paper · explained in 1 episode
• Generalization — 1× in this paper · explained in 13 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
• Sequential testing of conditionally constrained hypotheses
• Multiple testing in multi-stream sequential change detection
• An online generalization of the (e-)Benjamini-Hochberg procedure
• The Replay Gap: Static Evaluation of Model Switching in LLM Agents Scores the Wrong World
• Dynamic $e$-closure for online hypotheses with any-time-valid evidence: closure principles and projective mergers
• R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
• CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents
• PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents
• Admissibility and Complete Classes for False Discovery Rate Control with E-values
• AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay
• Anytime-valid FDR control with the stopped e-BH procedure
• Improving online FDR procedures via online analogs of e-closure and compound e-values
• AlphaSchema: Exploring the Space of Trading Semantics for LLM-Based Alpha Mining

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection