Third Moment Research Builds Self-Improving AI Agents Using OpenAI's GPT-6 Models

Third Moment Research is building a self-improving AI system designed around the idea that the best agents should be really good at specific work and should improve their capabilities the more they are used. The company uses OpenAI's latest models to understand agent behavior, identify recurring weaknesses, and automatically create thousands of synthetic scenarios around those problems. The team uses those scenarios to improve agents, repeating the process as new issues emerge.

Reducing runtime and token waste with Codex

One of Third Moment's early applications is in quantitative finance, a domain with a clear measure of success. The team uses Codex to find and address problems in the research environment. In one instance, it used Codex with GPT-5.6 to analyze thousands of recorded simulation trajectories alongside timestamps and the codebase. Codex uncovered a bottleneck: backtesting a trading strategy across a year of order-level US equity data took several hours. While waiting, agents repeatedly polled for completion, wasting tokens and filling their context with status checks. After profiling the backtest, Codex identified a caching optimization and a memory-packing technique, deployed the fix to production, and reduced the backtest from approximately 3 hours to approximately 3 to 5 minutes.

Keeping agents on task with Codex and GPT-6

Third Moment gives each agent the tools, information, and environment it needs for a specific job. For quantitative research, the team runs the default Codex harness inside a Dockerized environment. Agents receive a terabyte of data, documentation, and a research repository with modules for feature engineering, GPU-supported model training, trading strategies, and simulation. GPT-6 Astra, GPT-6 Sol, and GPT-6.1 Sol provide the reasoning, while the Codex harness gives agents tools to act, create plans, set objectives, spawn subagents, and compact context as work continues. To address agents that stop before completing a task, Third Moment treats Codex as a subagent within an outer harness powered by GPT-6 Sol or GPT-6.1 Sol. The outer harness examines the trajectory when a task is left unfinished and determines whether to retry, terminate the job, or escalate to human review.

Automating security testing with Daybreak

With 10,000 agents running autonomously, Third Moment needs a way to test the security of its research environments at scale. The team uses the Daybreak cybersecurity platform to automate that testing before simulations launch. The tests check whether an agent could break out of its research environment and access the wider network. "By using Daybreak, we're able to have agents themselves do penetration testing on the simulation and test the infrastructure and security of it," says Adam Khakhar, Co-founder of Third Moment Research.

Moving toward hundreds of thousands of collaborating agents

Third Moment's ambition extends to the specialized work companies do every day. For a retailer, that could mean making better supply chain decisions when inventory is short or a supplier is delayed. For an engineering team, it could mean finding performance bottlenecks in a large codebase. Building on the reasoning capabilities of GPT-6 Astra, GPT-6 Sol, and GPT-6.1 Sol, Third Moment plans to expand from individual investigations to hundreds of thousands of collaborating subagents. Its roadmap calls for trillions of tokens supporting chains of dozens of dependent experiments, with the goal of using that research to autonomously improve agents as new challenges arise.

Sources: OpenAI Blog