Chen: Reasoning provides essential robustness for long-horizon AI agents
Mark Chen · From Vibe Coding to Vibe Researching: OpenAI’s Mark Chen and Jakub Pachocki · Sep 25, 2025 · at 9:52
Mark Chen, Chief Research Officer at OpenAI, explains how reasoning enables AI agents to adapt after receiving negative environmental feedback across complex execution chains.
0:00 / 0:26exact quote · 26.1s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Reasoning is core to this ability to operate over a long horizon, because, you know, you imagine kind of yourself solving a math problem, where you try an approach, it doesn't work, and, you know, you have to think about, you know, what, what's the next approach I'm gonna take what are the mistakes in the first approach, and then you try another thing, and, you know, the world gives you some hard feedback, right, and then you keep trying different approaches, and the ability to do that over a long period of time Is reasoning and gives agents that robustness.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Mark Chen
Chen: GPT-5 Pro automates tasks that take physics students months
“And you know, we see physicists, mathematicians kind of repeating this experience over and over where they're trying GPT-Five Pro and saying, wow, this is something that the, you know, previous version of the models couldn't do. And it is a little bit of a lig…”
Chen: The future of scientific discovery will be 'vibe researching'
“I do think, you know, the future hopefully will be vibe researching.”
Chen: The future of AI will center on reasoning and agents
“So we think the future is about reasoning, more and more about reasoning, more and more about agents.”
Chen: Competitive coding and math benchmarks predict future research success
“I mean, I think it is important to note that these evals like you know, IOI, AtCoder, IMO are actually real world markers for success in future research.”
Chen: Earlier Codex models spent too little time on hard problems
“What we found is the latest, the previous generation of the codex models, they were spending too little time solving the hardest problems and too much time solving the easy, easy problems. And I think that, that is actually just probably out of the box what yo…”