References: The bull and the bear

For education only. Not investment, financial, or trading advice.

Source material

Primary source (open-source, Apache-2.0):
- TradingAgents, an open-source multi-agent LLM framework
  Authors: Yijia Xiao, Edward Sun, Di Luo, Wei Wang
  Organization: TauricResearch
  Repository: https://github.com/TauricResearch/TradingAgents
  Paper: "TradingAgents: Multi-Agents LLM Financial Trading Framework",
         arXiv:2412.20138 (https://arxiv.org/abs/2412.20138)
  License: Apache-2.0
  Pinned snapshot for this course: 7e9e7b8 (the framework as of 2026-05-01)

All code shown in this lesson is quoted from the framework at the pinned
snapshot above, under the Apache-2.0 license, with attribution. Clawdemy's
lesson prose is original. We teach the architecture only; we make no
investment, financial, or trading claims, and we report no performance results.

How to open it (no account or Git needed)

The framework is public and free to read. You do not need a GitHub account, the tool called Git, or any programming knowledge: open the link below in your browser and read the files like ordinary web pages.

• github.com/TauricResearch/TradingAgents (pinned snapshot). This link points to one frozen version of the project, marked by the short code 7e9e7b8.

The files this lesson reads

At the pinned snapshot:

• tradingagents/agents/researchers/bull_researcher.py: the agent told to build the case for, reading the four reports plus the bear’s last argument.
• tradingagents/agents/researchers/bear_researcher.py: the mirror agent, told to build the case against.
• tradingagents/graph/conditional_logic.py: should_continue_debate, the check that compares a turn counter against a round limit and routes to the next speaker or to the judge.
• tradingagents/agents/managers/research_manager.py: the Research Manager, the separate judge that reads the transcript and commits to one stance, written as the investment plan.

Read this next

• TradingAgents repository (TauricResearch). The full source, at the pinned snapshot. The four files above are the ones this lesson quotes.
• TradingAgents paper (arXiv:2412.20138) by Yijia Xiao, Edward Sun, Di Luo, and Wei Wang. The framework’s own description of its design, including the research debate.

Adjacent topics

Where this sits inside this track.

• How an agent fetches its own data. The previous lesson: how a single analyst gathers its facts with tools. This lesson is the first time several agents interact.
• The trader. The next lesson: the judge produced a plan, but a plan is not yet an action. The trader turns the judgment into a concrete, sized course of action.
• Why split one AI into many. Lesson 1 introduced the roster and the deep-versus-fast model split that this lesson puts to work at the judgment point.