Mobius
Summary
Mobius is a tool that lets users describe a trade and automatically builds, backtests, and runs it.
Similar Articles
Built a 10-agent pipeline for portfolio construction — macro, screener, 6 analysts, orchestrator, constructor — runs across 6 LLM providers
1rok is a TypeScript framework that enables running multi-agent portfolio construction pipelines across multiple LLM providers to benchmark their performance on financial tasks like stock selection and position sizing.
QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies
QuantCode-Bench is a new benchmark of 400 tasks evaluating LLMs on generating executable algorithmic trading strategies for the Backtrader framework, testing syntactic correctness, backtest execution, trade presence, and semantic alignment. The study finds that current models' main limitations lie in correctly operationalizing trading logic and API usage rather than syntax.
Built an Open-Source Devil's Advocate for Stock, Fund and Investing Deals
A multi-agent open-source tool built with OpenAI agents and Valyu financial search to stress-test investment theses by acting as Bull, Bear, House View Checker, Synthesizer, and binding Devil's Advocate.
@eigentopology: Introducing Automode on @thesis_labs! Watch Thesis run autonomous ML research on an Optiver trading dataset Try it toda…
Thesis Labs launched Automode, a system that autonomously conducts ML research on Optiver’s trading dataset.
TradingAgents: Multi-Agents LLM Financial Trading Framework
This paper introduces TradingAgents, a multi-agent LLM framework that simulates real-world trading firms to improve stock trading performance. It utilizes specialized agents for analysis and risk management, demonstrating superior results in cumulative returns and Sharpe ratio compared to baselines.