A Third Moment Research olyan rendszert épített, amelyben több ezer autonóm AI-ügynök dolgozik egyidejűleg 36-48 órás kutatási feladatokon. A cég az OpenAI GPT-6 Astra, GPT-6 Sol és GPT-6.1 Sol modelljeit használja, a környezet biztonságát pedig a Daybreak platformmal teszteli. A rendszer a korábbi hibákból automatikusan szintetikus teszthelyzeteket generál, így az ügynökök a használat során folyamatosan fejlődnek.
A gyakorlatban az ügynökök képesek kódalapú szűk keresztmetszetek feltárására, optimális gyorsítótárazás bevezetésére és önálló alügynökök indítására. Egy pénzügyi szimuláció során például egy 3 órás folyamatot 3-5 percre tudtak lecsökkenteni. Ha egy ügynök megakad, egy külső felügyelő architektúra dönt a folyamat újraindításáról, leállításáról vagy emberi felülvizsgálatról.
A vállalat célja, hogy a jövőben több száz ezer együttműködő alügynököt futtasson. Ez a megközelítés lehetővé teszi a kutatási irányok automatikus feltárását, kiszűrve a nem nyilvánvaló összefüggéseket is.
Az eredeti szöveg (OpenAI)
With GPT‑6 Astra and GPT‑6.1 Sol, Codex, and Daybreak for cybersecurity, this AI lab builds agents that focus for days and improve with use.
Every company has its own workflows, tools, edge cases, and definitions of success. (opens in a new window)Third Moment Research(opens in a new window) believes the best agents should be really good at that specific work and should improve their capabilities the more they’re used.
The company is building a self-improving AI system around that idea, using 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.
Codex, GPT‑6 Astra, GPT‑6 Sol, and GPT‑6.1 Sol support the system’s research and computational work, enabling Third Moment to run 10,000 agents at once on investigations lasting 36-48 hours. The company also uses Daybreak to test the security of the environments where agents work.
One of Third Moment’s early applications is in the field of quantitative finance given the clear measure of success. This domain provides a concrete setting to study how agents work and where they struggle. The team uses Codex to find and address problems in the research environment.
In one instance, it used Codex with GPT‑5.6, the latest GPT model at the time, to analyze thousands of recorded simulation trajectories (the agents’ actions and the environment’s responses) 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 and analyzing its inputs and usage, Codex identified a caching optimization and a memory-packing technique. It experimented with solutions and deployed the fix to production, reducing the backtest from approximately 3 hours to approximately 3 to 5 minutes. This reduced token use and context pollution, freeing more of the agents’ token budget for further experiments.
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.
In that research environment, agents work to improve a baseline trading system built by Third Moment’s engineers. They test trading strategies on historical data, assess whether an improvement is meaningful or noise, and use each result to choose the next experiment. According to Adam, their work has improved the baseline trading system.
Before GPT‑5.5, Adam says models could only execute experiments prescribed by a user. With GPT‑5.5 and GPT‑5.6, models working with the Codex harness could use results to design follow-up experiments. Now with GPT‑6 Astra, GPT‑6 Sol, and GPT‑6.1 Sol, agents can investigate root causes through hundreds of experiments running in parallel with subagents.
That progression has helped agents explore research directions the team hadn’t anticipated. In one session, GPT‑6.1 Sol identified the impact of non-displayed trades on an exchange where those trades accounted f
