The Self Driving Portfolio: Agentic Architecture for Institutional Asset Management
cs.AI, cs.MA, q-fin.GN, q-fin.PM
Submitted: 2026-04-02
Updated: 2026-09-21
Comments: 39 pages, 11 exhibits
Code: https://github.com/openclaw/openclaw
License: http://creativecommons.org/licenses/by/4.0/
The gist: Agentic AI shifts the investor's role from analytical execution to oversight.
Terminology
Abstract
Agentic AI shifts the investor's role from analytical execution to oversight. We present an agentic strategic asset allocation pipeline in which 44 specialized agents produce capital market assumptions, construct portfolios using 21 competing methods, and critique and vote on each other's outputs. A researcher agent proposes new portfolio construction methods not yet represented, and a meta agent compares past forecasts against realized returns and rewrites agent code and prompts to improve future performance. The entire pipeline is governed by the Investment Policy Statement - the same document that guides human portfolio managers can now constrain and direct autonomous agents.
Sources
- Matching adjacent cards
- Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- Levels of Autonomy for AI Agents
- Large Language Model based Multi-Agents: A Survey of Progress and Challenges
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- Understanding the planning of LLM agents: A survey
- LLM Voting: Human Choices and AI Collective Decision Making
- Diophantine equations over the generalized Fibonacci sequences: exploring sums of powers
- Defensible Design for OpenClaw: Securing Autonomous Tool-Invoking Agents
- The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- TradingAgents: Multi-Agents LLM Financial Trading Framework
- FinRobot: AI Agent for Equity Research and Valuation with Large Language Models
- DatedGPT: Preventing Lookahead Bias in Large Language Models with Time-Aware Pretraining
- Fine Boundary Regularity For The Fractional (p,q)-Laplacian
- Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw
- A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist
- Argument-Based Comparative Question Answering Evaluation Benchmark
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