Introducing Forezai · TradingAgents — a committee of LLMs decides paper-trades
Up next
Author
Share article
The post has been shared by 0 people.
Facebook 0
X (Twitter) 0
Pinterest 0
Mail 0

📊 Full opportunity report: Introducing Forezai · TradingAgents — a committee of LLMs decides paper-trades on ThorstenMeyerAI.com — validation score, market gap, and execution plan.

TL;DR

Forezai has launched TradingAgents, a system where a committee of large language models (LLMs) collectively decide simulated trades. This development aims to explore AI decision-making in trading, separate from market prediction claims.

Forezai has introduced TradingAgents, a new platform that employs a committee of large language models (LLMs) to generate paper-trades based on structured, multi-role reasoning. This system aims to evaluate whether LLMs, acting collectively, can produce trading decisions comparable to or better than random chance, without claiming market prediction capabilities.

The TradingAgents framework is a fork of an open-source multi-agent research system originally developed by TauricResearch, built on top of LangGraph. It involves multiple specialized LLM roles, including analysts, debate agents, risk teams, and decision syntheses, which work together to analyze data and decide on trading actions.

Forezai’s version adds operational features such as an autonomous daily scheduler, paper trading interfaces with filtering and risk management, audit logs, and a web dashboard. It supports multiple modes, including local simulation, Alpaca paper trading, and a ‘shadow’ mode for parallel testing, with safeguards to prevent accidental real-money trading. The platform runs locally and emphasizes transparency and reproducibility in research.

While the system does not aim to predict markets, it tests whether a structured, multi-agent LLM approach can produce decisions at least no worse than random, providing insights into AI reasoning in trading contexts. The project is still in early phases, focusing on research rather than live trading.

Introducing Forezai · TradingAgents — Thorsten Meyer AI
AGENTS
● ANNOUNCEMENT / MAY 2026
THORSTEN MEYER AI · FOREZAI · § 03
FOREZAI · 03
TRADINGAGENTS · LAUNCH
Research Series · Companion to Polybot Week 1-2 · 2026-05-17

Introducing Forezai · TradingAgents.
A committee of LLMs
decides paper-trades.

After two weeks of finding out most parametric strategies don’t work, the obvious next research question: can multi-agent LLM judgment do any better?
A fork of the open-source TradingAgents framework (TauricResearch): thirteen LLM agents in four stages — four parallel analysts · a bull-bear debate with research-manager arbitration · a three-voice risk team · a two-layer trader + portfolio-manager decision. The fork keeps the agent graph intact and adds the operational layer the upstream doesn’t ship: an autonomous loop · a multi-broker abstraction · a local web dashboard · Codex OAuth · MCP plug-ins · 520+ unit tests. The question is narrower than “do LLMs predict the market” — that prior is “no, with high confidence.” The narrower question is: when LLMs are structured into specialised adversarial roles, does the committee produce decisions at least no worse than a coin flip after fees? Honest priors before running: it might fail too. If it appears to work, the most likely explanation is variance.
Thorsten Meyer AI Forezai · TradingAgents Apache-2.0 fork · upstream cited Companion piece · ~2,500 words Polybot · § 03
This is not financial advice. Nothing in this announcement should be used to inform real trading decisions. The software described trades simulated money by default. If you reconfigure it to trade real money, you should expect to lose that money — regardless of how clever any individual agent’s reasoning looks. Algorithmic trading is zero-sum after fees and structurally hostile to part-time retail strategies.
13 agents
Specialised roles in four stages
Analysts · Debate · Risk · Decision
78% / -33%
Polybot prior: fleet win rate
combined with -33% bankroll
520+
Passing unit tests across engine,
services, HTTP routes (starting baseline)
€0 floor
LLM cost on Codex OAuth
(falls back to public API per token)
FOREZAI / TRADINGAGENTS· APACHE 2.0 FORK· UPSTREAM TAURIC RESEARCH· LANGGRAPH· 13 AGENTS / 4 STAGES· 4 PARALLEL ANALYSTS· BULL-BEAR DEBATE· 3-VOICE RISK TEAM· TRADER + PORTFOLIO MANAGER· 5-TIER FINAL RATING· ALPACA PAPER + LOCAL + SHADOW· LIVE ENDPOINTS HARD-REFUSED· FASTAPI + REACT VIA CDN· CODEX OAUTH· MCP PLUG-IN REGISTRY· 520+ UNIT TESTS· POLYBOT WEEK 1: 21 EXPERIMENTS· WEEK 2: -33% BANKROLL· 78% FLEET WIN RATE· HONEST RESEARCH, NOT EDGE· FOREZAI / TRADINGAGENTS· APACHE 2.0 FORK· UPSTREAM TAURIC RESEARCH· LANGGRAPH· 13 AGENTS / 4 STAGES· 4 PARALLEL ANALYSTS· BULL-BEAR DEBATE· 3-VOICE RISK TEAM· TRADER + PORTFOLIO MANAGER· 5-TIER FINAL RATING· ALPACA PAPER + LOCAL + SHADOW· LIVE ENDPOINTS HARD-REFUSED· FASTAPI + REACT VIA CDN· CODEX OAUTH· MCP PLUG-IN REGISTRY· 520+ UNIT TESTS· POLYBOT WEEK 1: 21 EXPERIMENTS· WEEK 2: -33% BANKROLL· 78% FLEET WIN RATE· HONEST RESEARCH, NOT EDGE·
FIG. 01 — THE 13-AGENT COMMITTEE
Thirteen specialised roles · four stages · biases made to argue in public
The architecture forces the system to articulate its reasoning rather than relying on what a single context window happens to recall
Stage 1 · Four analysts in parallel4 agents
Market
Structure, ranges, regime indicators
News + Insider
News flow, filings, insider activity
Fundamentals
Balance sheet, earnings, ratios
Social Sentiment
Social-media tone, retail signal
↓
Stage 2 · Bull-bear debate + research-manager arbitration3 agents
Bull researcher
Argues upside thesis from analyst reports
Bear researcher
Argues downside thesis from same reports
Research manager
Arbitrates · writes single synthesis
↓
Stage 3 · Three-voice risk team3 agents
Aggressive
Looks for upside · accepts variance
Conservative
Looks for downside · protects capital
Neutral
Balances · forces downside articulation
↓
Stage 4 · Two-layer decision2 agents
Trader
Three-tier proposal · buy / hold / sell
Portfolio manager
Five-tier rating + price target + horizon · sees arguments only, never raw data
The portfolio manager only sees the arguments, never the raw data — which forces the committee to make its reasoning explicit rather than relying on a single context window’s recall. The upstream framework ships the agent graph; it does not ship the operational machinery to run that graph on autopilot, observe its results honestly, store them for later inspection, or prevent the operator from accidentally trading real money. That gap is what the Forezai fork fills.
FIG. 02 — THE POLYBOT PRIOR · WHY THIS IS A DIFFERENT BET
Two weeks of paper-trading prediction markets · the trap underneath the headline numbers
25 experiments · 78% fleet-wide win rate · -33% bankroll · most parametric strategies are structurally negative-expectation when measured honestly
The flattering number
78%
Fleet-wide win rate · week 2
“You can win four out of five trades and still go broke, because the one loss is bigger than the four wins put together.” Win rate without P&L context is a mechanical illusion.
The honest number
−33%
Fleet bankroll · week 2 close
The strongest possible demonstration of the trap. A parametric trading strategy that looks compelling in a backtest will almost always fail to survive a fresh sample. Most “edges” are mechanical artefacts.
Week 1: 21 parallel strategy experiments · early winners mostly mechanical illusions · exactly one strategy (a fair-value taker on BTC) showed the mathematical signature of real edge over a few hundred settled trades. Week 2: same fair-value strategy with more data collapsed. A separate mid-week hypothesis (market-making) also failed cleanly. Fleet ended week 2 at roughly negative thirty-three percent of bankroll. The honest research finding wasn’t on the winning side — it was on the losing side. Adding more parameters to Polybot wouldn’t change that. TradingAgents is asking a separable question.
FIG. 03 — WHAT THE FORK ADDS · THE OPERATIONAL LAYER
Six layers the upstream framework doesn’t ship
Same agent graph, intact. The fork makes it a research instrument rather than a tech demo.
01 · Loop
An autonomous loop
Scheduler · watchlist · auto-trader maps ratings to paper orders · allow-list filtering · per-ticker cooldowns · sector caps · cash checks · position manager evaluates open positions every 60s for TP / SL / max-hold. Append-only audit logs.
02 · Brokers
Multi-broker abstraction
Three modes: local Python broker (yfinance fills, JSON-persisted) · Alpaca paper-trading adapter · “shadow” mode running both in parallel with divergence view. Real Alpaca live endpoints are hard-refused at multiple layers.
03 · Dashboard
A local web dashboard
FastAPI backend · React via CDN, no Node toolchain · SVG equity curve · rolling-peak drawdown · win-rate by rating / ticker / model · exit-reason breakdown · LLM cost vs realised P&L joined by run ID. Runs locally; nothing sent to a cloud service.
04 · Codex
Codex OAuth
Runs the engine on a ChatGPT Pro subscription via the Codex backend. LLM cost floor effectively zero if you already have ChatGPT Pro. Token stored encrypted locally. Falls back to the regular OpenAI API if you’d rather pay per token.
05 · Alerts
Multi-channel alerts
Slack · Discord · SMTP email · configurable filter on rating events and order fills · append-only history kept locally. Webhook URLs masked in API responses so a screenshot can’t accidentally leak credentials.
06 · MCP
MCP plug-ins
Registry for adding Anthropic Model Context Protocol servers (Kensho · Aiera · FactSet · Morningstar · LSEG) as analyst tools. Plug-ins advertise category (fundamentals · news · market data · social) · probe endpoint tests credentials.
Honest-by-design touches: every generated report prepends “Research, not advice” and appends a footer with version, commit, provider, models used, run ID, and cost. Closed trades carry the same metadata. 520+ passing unit tests across engine, services, and HTTP routes. The intent: when the system loses money, the journal makes it impossible to pretend it didn’t.
FIG. 04 — HONEST PRIORS · BEFORE RUNNING THIS IN ANGER
Three priors stated before the data starts arriving
The bias of the project: when the data says no, the dashboard says no, the article says no
1
It might fail too. LLMs are not oracles, and a sophisticated framework around language-model outputs does not change the underlying error rate of the model. Sample is still everything. The framework’s outputs are subject to the same statistical noise as any prediction system over small samples.
Highest likelihood
2
If it appears to work, the most likely explanation is variance. The same trap that caught the first article’s candidate edge applies here. A high win rate over fifty trades means much less than it looks. Without out-of-sample confirmation, a flattering early sample tells you almost nothing about whether the system has real edge.
Second-most likely
3
If it appears to work for the right reasons — empirical win rate matches stated confidence, and alpha-versus-benchmark persists across non-overlapping samples — that would be a meaningful research finding. Whether that happens, I don’t know. The point of putting it in the open is that the data will say.
Genuinely open
This is explicitly not a launch announcement for a product anyone should connect a real brokerage account to. The Alpaca live endpoints are hard-refused at multiple layers in the code, and the design choice is deliberate. The right next step is data, not deployment. The bias of the whole project is straightforward: when the data says no, the dashboard says no, the article says no, and no one tries to retroactively rescue the thesis. That’s the contribution.
FIG. 05 — WEEK THREE · WHAT THE METHODOLOGY WILL MEASURE
Four concrete measurements before publishing findings
The hope: write the week-three article from a position of “here’s what the data says”. The fear: another candidate falsified at higher sample. Both outcomes are publishable.
M1 · Sample discipline
Small watchlist for a few weeks before publishing
A handful of tickers across two or three sectors. Long enough to gather sample, narrow enough to keep attention on what’s actually happening per agent. Avoid the noise of a 65-ticker autonomous loop until the smaller version has been read carefully.
M2 · Calibration view
Stated confidence vs. realised win rate
When the system says “75% confident”, do the trades actually win 75% of the time? Same measurement applied to Polybot’s fair-value model. If the model is systematically over-confident, that bias dominates everything downstream.
M3 · Cost accounting
Cost per ticker · per rating · per profitable trade
With Codex OAuth the marginal LLM cost is effectively zero. With the public OpenAI API, each run is hundreds of agent turns. The honest question: does this scale economically if you ever did run it at real cost?
M4 · Non-overlapping windows
Alpha vs benchmark · out-of-sample
Not within-sample alpha — trivially inflatable. Hold out one period entirely, run the system on the next, then check whether the held-out result matches the in-sample stats. If they diverge sharply, the in-sample was curve-fit.
Open under Apache-2.0 with upstream cited from every relevant surface. Not open: the operator’s running results, the specific watchlist, the per-agent prompt customisations, the alert channels, the trade journals — kept local for the same reason Polybot’s per-experiment data is kept local. Publishing exact configurations encourages people to copy them with real money, which is the opposite of what an honest research project should do. Summary findings will be published. Recipes will not.
The bet is on a different mechanism, not a different parameter setting. The point is not to find a money-printing AI. The point is to put honest measurements of these systems into the public record — so the next person looking at the space starts a step further along than the last.
Thorsten Meyer AI · Introducing Forezai · TradingAgents · § 03
Source dossier & project notes
  • Forezai · TradingAgents fork — Apache-2.0 license preserved · GitHub published under same author as Polybot · upstream cited from README · marketing pages · generated report footers · forezai.com
  • TradingAgents upstream — TauricResearch team · multi-agent stock-research framework on LangGraph · the agent graph is intact in the fork · upstream license requirements (notice file · attribution · patent-grant clauses) preserved if anyone forks again
  • Polybot · Week 1 — 21 parallel strategy experiments on Polymarket 5-minute Up/Down · early winners mostly mechanical illusions · one BTC fair-value taker showed mathematical signature of edge over a few hundred settled trades
  • Polybot · Week 2 — fair-value strategy collapsed at higher sample · market-making hypothesis failed cleanly · fleet ended at ~negative 33% of bankroll · 78% fleet-wide win rate combined with deeply negative P&L · “you can win four out of five trades and still go broke”
  • Architecture · Stage 1 — Four analysts in parallel: market structure · news + insider · fundamentals (balance sheet + earnings) · social-media sentiment · each writes a short structured report independently
  • Architecture · Stage 2 — Bull-bear debate: two researcher agents argue opposing theses from the analyst reports · a research-manager agent arbitrates and writes a single synthesis
  • Architecture · Stage 3 — Three-voice risk team: aggressive (upside, accepts variance) · conservative (downside, protects capital) · neutral (balances) · forces explicit articulation of downside before any order is proposed
  • Architecture · Stage 4 — Two-layer decision: trader agent produces three-tier proposal (buy / hold / sell) · portfolio-manager agent synthesises into final five-tier rating with price target and time horizon · PM sees arguments only, never raw data
  • Operational layer — Autonomous loop · multi-broker abstraction (local Python / Alpaca paper / shadow mode) · FastAPI + React-via-CDN web dashboard · Codex OAuth on ChatGPT Pro · multi-channel alerts (Slack · Discord · SMTP) · MCP plug-in registry (Kensho · Aiera · FactSet · Morningstar · LSEG)
  • Engineering baseline — 520+ passing unit tests across engine, services, HTTP routes · honest-by-design touches: “Research, not advice” prepended to every report · footer with version, commit, provider, models used, run ID, cost
  • Hard-refused live trading — Real Alpaca live endpoints hard-refused at multiple layers · operator must deliberately override the refusal in more than one place to actually risk real money
  • Week three methodology — Small watchlist · calibration view (stated confidence vs realised win rate) · cost accounting per ticker / rating / profitable trade · out-of-sample alpha across non-overlapping windows
  • Stance — Summary findings published · recipes kept local · the bias is straightforward: when the data says no, the dashboard says no, the article says no, no one tries to retroactively rescue the thesis
Colophon

Set in Source Serif 4 (display, italic accent), EB Garamond (body), IBM Plex Sans (UI labels), IBM Plex Mono (mastheads, ticker, stamps, plug-in tags). Paper-cool gray-cream #e6e7e4.

Chromatic register: structural-slate dominant (committee-architecture analysis), empirical-clay for the Polybot prior forensic, labor-rose for the cautionary “expect to lose money” stance and the regulatory disclaimers, transition-bronze for the week-three forward-shape methodology, alternative-sage for the open-source / honest-measurement positive signal.

Key frame:

FOREZAI / TRADINGAGENTS 13-AGENT COMMITTEE POLYBOT PRIOR OPERATIONAL LAYER EXPECT TO LOSE MONEY CALIBRATION VIEW BULL-BEAR DEBATE HARD-REFUSED LIVE APACHE 2.0 HONEST MEASUREMENTS

Implications for AI in Trading Decision-Making

This development is significant because it explores a novel approach to AI-driven trading decisions, emphasizing reasoning and argumentation over prediction. If successful, it could influence how AI tools are used in finance, shifting focus from market forecasting to decision processes and explainability. It also provides a controlled environment to study the limitations and capabilities of LLMs in complex, multi-step reasoning tasks, which has broader implications beyond trading.

3-Tier Foldable Paper Display Stand - Portable Adjustable Showcase for Trade Shows, Cosmetics & Handbags, Retail Merchandising Platform for Boutique, Exhibitions (L197 in * W31.5 in * H46 in)

3-Tier Foldable Paper Display Stand – Portable Adjustable Showcase for Trade Shows, Cosmetics & Handbags, Retail Merchandising Platform for Boutique, Exhibitions (L197 in * W31.5 in * H46 in)

Certified Kraft Paper & Honeycomb Bionic Technology deliver exceptional structural integrity – ensuring even load distribution, sustained operational…

AmazonView Latest Price

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Background on AI and Algorithmic Trading Experiments

Previous research by Thorsten Meyer and others has shown that simple parametric trading strategies often fail to produce sustained profits, with many seemingly promising backtested edges collapsing in live testing. This has led to skepticism about AI and rule-based strategies in trading. The current project shifts focus from explicit rules to structured reasoning among multiple LLMs, aiming to see if collaborative argumentation can yield better-than-random decisions.

Open-source efforts like TauricResearch’s TradingAgents framework have demonstrated the feasibility of multi-agent AI systems in finance research. Forezai’s fork extends this by adding operational capabilities, making it suitable for systematic experimentation and analysis.

“This system does not promise predictions but tests whether a committee of LLMs can make decisions at least as good as a coin flip, based solely on structured reasoning.”

— Thorsten Meyer

Building Winning Algorithmic Trading Systems: A Trader's Journey From Data Mining to Monte Carlo Simulation to Live Trading (Wiley Trading)

Building Winning Algorithmic Trading Systems: A Trader's Journey From Data Mining to Monte Carlo Simulation to Live Trading (Wiley Trading)

AmazonView Latest Price

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Unclear Aspects of AI Decision Effectiveness

It remains uncertain whether the multi-LLM committee can produce decisions that outperform random chance in real or simulated markets over longer periods. The effectiveness of this approach in actual trading remains untested, and results are still preliminary. Additionally, the broader implications for market prediction or profitability are not yet established, as the system is designed primarily for research and understanding AI reasoning.

Agentic Architectural Patterns for Building Multi-Agent Systems: Proven design patterns and practices for GenAI, agents, RAG, LLMOps, and enterprise-scale AI systems

Agentic Architectural Patterns for Building Multi-Agent Systems: Proven design patterns and practices for GenAI, agents, RAG, LLMOps, and enterprise-scale AI systems

AmazonView Latest Price

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Next Steps for Testing and Validation

Forezai plans to run systematic experiments using the TradingAgents system, analyzing the decision quality over extended simulated periods and different market conditions. Future work may include refining agent roles, expanding the decision framework, and publishing detailed results to assess the potential of multi-LLM committees in trading contexts. The team also aims to improve operational stability and user interface features for broader research use.

The New Trading for a Living: Psychology, Discipline, Trading Tools and Systems, Risk Control, Trade Management (Wiley Trading)

The New Trading for a Living: Psychology, Discipline, Trading Tools and Systems, Risk Control, Trade Management (Wiley Trading)

AmazonView Latest Price

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Key Questions

Can this system predict market movements?

No, the system does not aim to predict market movements but to test whether a committee of LLMs can make reasonable trading decisions based on structured reasoning.

Is this meant for live trading or research?

This platform is designed for research purposes, running in simulated environments with safeguards to prevent real-money trading.

What makes this different from traditional algorithmic trading?

Unlike rule-based algorithms, this system uses multiple specialized LLMs to argue and synthesize decisions, focusing on reasoning processes rather than explicit market prediction rules.

Will this system be available for public use?

Currently, it is a research prototype; future plans for public access depend on further development and validation results.

What are the limitations of this approach?

It is uncertain whether the reasoning-based decisions will translate into profitable trading, and the system’s effectiveness in live markets remains unproven.

Source: ThorstenMeyerAI.com

Nothing in this article is financial or investment advice. Cryptocurrency and precious-metal investments carry significant risk — do your own research and consider a licensed advisor.
You May Also Like
The OAuth Permission Apocalypse.

The OAuth Permission Apocalypse.

An analysis of the growing risk from overly permissive OAuth permissions, exemplified by recent supply chain breaches, and why industry-wide change is urgent.
The Roblox Cheat That Broke Vercel.

The Roblox Cheat That Broke Vercel.

A Roblox auto-farm script downloaded by a Vercel employee via Context.ai led to a major breach, exposing customer credentials across multiple platforms in April 2026.
The Anthropic-Blackstone-Goldman JV: Reverse-Engineering the $1.5B Enterprise AI Services Structure

The Anthropic-Blackstone-Goldman JV: Reverse-Engineering the $1.5B Enterprise AI Services Structure

A new $1.5 billion joint venture by Anthropic, Blackstone, and Goldman Sachs aims to embed AI engineering in mid-sized firms, signaling a strategic shift in enterprise AI services.
Agentic Loop Failure Modes: A Production Taxonomy at the End of Year One

Agentic Loop Failure Modes: A Production Taxonomy at the End of Year One

A new taxonomy of failure modes in production agentic AI systems has been developed after one year of deployment, aiding debugging and architectural design.