Intel / repo

TradingAgents

Source: arxiv.org
Author: Tauric Research
Date: Indexed Apr 14, 2026

Context

TradingAgents, a research framework from Yijia Xiao, Edward Sun, Di Luo and Wei Wang at UCLA, MIT and Tauric Research, organizes AI stock analysis around a sequence of reports and challenges. Specialist agents examine financial statements, news, sentiment and price indicators. Two researcher agents argue for and against an investment, giving the trader competing interpretations before it proposes a decision.

The communication design makes those handoffs explicit. Agents retrieve structured reports from shared state, while debates use ordinary language and have their outcomes recorded. Risk reviewers then challenge the proposed trade, and a fund-manager adjusts it. The paper presents this structure as a way to preserve relevant evidence through a long decision process.

Terms in this piece · Glossary

AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.

Read the source arxiv.org