REVIEW 11 cited by
TradingAgents: Multi-Agents LLM Financial Trading Framework
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Significant progress has been made in automated problem-solving using societies of agents powered by large language models (LLMs). In finance, efforts have largely focused on single-agent systems handling specific tasks or multi-agent frameworks independently gathering data. However, the multi-agent systems' potential to replicate real-world trading firms' collaborative dynamics remains underexplored. TradingAgents proposes a novel stock trading framework inspired by trading firms, featuring LLM-powered agents in specialized roles such as fundamental analysts, sentiment analysts, technical analysts, and traders with varied risk profiles. The framework includes Bull and Bear researcher agents assessing market conditions, a risk management team monitoring exposure, and traders synthesizing insights from debates and historical data to make informed decisions. By simulating a dynamic, collaborative trading environment, this framework aims to improve trading performance. Detailed architecture and extensive experiments reveal its superiority over baseline models, with notable improvements in cumulative returns, Sharpe ratio, and maximum drawdown, highlighting the potential of multi-agent LLM frameworks in financial trading. TradingAgents is available at https://github.com/TauricResearch/TradingAgents.
Forward citations
Cited by 11 Pith papers
-
Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents
Malicious tools can systematically extract isolated LLM-agent long-term memory via persistence, pure-anchor retrieval steering, and reactivation payloads, reaching 80% extraction with unlimited triggers and 47% with 20.
-
CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents
CLQT is a new closed-loop, cost-aware benchmark that diagnoses LLM trading agent capabilities through strategy-consistent metrics and hash-verifiable trails rather than outcome rankings.
-
Can Large Language Models Execute Parent Orders?
PACE, a planner–executor LLM framework, beats TWAP, Almgren–Chriss, and ML execution baselines by up to ~0.65 bps on Shenzhen parent orders without task-specific training.
-
NextFund: A Unified Performance Tracking Platform for Agentic Portfolio Management
NextFund unifies live multi-market data, multi-agent portfolio reasoning, and end-to-end decision traces with an interactive Trading Arena for fairer LLM agent benchmarking.
-
ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism
An LLM trading system that selects agents through an internal contest scored by a zero-intelligence trader and LightGBM predictions reports 52.8% returns and Sharpe 3.12 on A-shares over six months.
-
StockSim: A Dual-Mode Order-Level Simulator for Evaluating Multi-Agent LLMs in Financial Markets
StockSim provides a dual-mode simulated stock market, with order-level and candlestick-level execution, for evaluating LLM trading agents.
-
To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisions
LLM-discovered stochastic models of price paths provide risk metrics that improve trader-agent decisions, raising average Sharpe ratios from 0.88 to 1.40 in the paper's backtests.
-
EconGym: A Scalable AI Testbed with Diverse Economic Tasks
EconGym introduces a modular, scalable economic testbed with 11 role types and 25+ tasks, benchmarking AI, economic, and hybrid policies up to 10k agents.
-
Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models
A two-framework testbed comparison claims mem0 is Pareto-optimal over Graphiti for distributed LLM agents because its lower cost is paired with accuracy that is not significantly different.
-
SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control
A multi-agent RL workflow that interleaves single-agent updates, applied to mobile GUI control, achieves SOTA zero-shot performance and a +14.8 MATH500 gain.
-
Integrating Large Language Models in Financial Investments and Market Analysis: A Survey
A survey that organizes recent LLM-in-finance research into four framework categories and summarizes the reported methods, datasets, and performance of about 30 systems.
Discussion (0). Sign in to comment.