Little J, a competing product under JZL, ranked first globally in the first stage of the LTP Liquidity Arena 2026 multi-agent live quantitative trading championship and advanced to the second round.
Liquidity Arena 2026 is described as the world’s first and currently the largest global live quantitative trading competition for AI agents and autonomous trading systems. More than 200 teams entered this year’s event, including hedge funds, private funds, proprietary trading firms, professional financial institutions, and university research teams from China and overseas. Unlike traditional backtesting or paper-trading contests, Liquidity Arena runs in real market conditions and places greater weight on live execution, strategy adaptation, and risk management in AI trading systems. The event rankings can be viewed on the LTP Liquidity Arena Leaderboard.
How Little J adjusted its trading approach
Mason, the lead PM for Little J, remained involved throughout the project’s iteration cycle, from pre-competition framework design to strategy adjustments during the contest, execution issue handling, and risk control. Before the competition began, Mason led the development of the Nexus multi-agent collaboration framework, setting an initial structure for coordination among different agents, information-sharing logic, and a multi-agent mechanism that combined proactive and responsive elements. That framework became the base for later live trading operations.
After trading began, Little J went through multiple rounds of strategy iteration based on real market feedback. Its development path moved through short-cycle automated trading, range-bound strategy, grid strategy, and trend strategy.
- Short-cycle automated trading
- Range-bound strategy
- Grid strategy
- Trend strategy
During that process, the team encountered issues including order execution, adaptation to trading rules, position management, and mismatches between strategy and market conditions. Mason used trading logs and actual performance to identify those issues and pushed changes to both execution logic and strategy design. As market conditions shifted, the team also moved from a trading approach geared more toward range-bound conditions to a trend-based framework, while adding multi-asset allocation and risk diversification mechanisms.
Round-two qualification and next steps
In the end, Little J entered the second round of the LTP Liquidity Arena in first place, completing what the team described as a relatively complete live-trading validation of a multi-agent system.
The team said its next work will continue to focus on agent collaboration, strategy adaptability, and risk control.
Disclaimer: Markets carry risk, and caution is advised in investing. This article does not constitute investment advice. Users should consider whether any opinions, views, or conclusions in this article fit their own circumstances. Any investment decisions made on that basis are the user’s own responsibility.
