Sign in

agentic learning ai lab

@agentic-ai-lab.bsky.social
135 followers 64 following 22 posts

AI research lab @nyu.edu led by @mengyer.bsky.social | Partially run by students | agenticlearning.ai

PostsRepliesMedia
Reposted by agentic learning ai lab
Outerloop @outerloop.science · 18/09/2026
Outerloop 0.2.0 is out. A lifecycle release: research agents now have persistent states instead of running once and exiting, and one unified message inbox: agent-to-agent messages, kernel notices, gate verdicts, reviewer findings, branch moves and CI results.
032
agentic learning ai lab @agenticlearning.ai · 10/09/2026
Outerloop is the open autoresearch stack we build and run in the lab. Check it out and deploy on your own cluster! outerloop.science
020
Reposted by agentic learning ai lab
NYU Center for Data Science @nyudatascience.bsky.social · 17/08/2026
The DOE has selected the first round of projects for its Genesis Mission, a national push to speed up scientific discovery with AI. Two CDS faculty are on board: ⭐️ Mengye Ren (@mengyer.bsky.social) on MARS ⭐️ Juliana Freire on DAISY www.nyu.edu/about/news-p...
032
agentic learning ai lab @agenticlearning.ai · 07/07/2026
Kbbq time! @jacklu-me.bsky.social @yingwww.bsky.social @mengyer.bsky.social
130
agentic learning ai lab @agenticlearning.ai · 04/07/2026
Agentic Learning AI Lab @agentic_ai_lab presents at #ICML2026 in Seoul ✈️🇰🇷 Come check out our research 🧵👇
130
Reposted by agentic learning ai lab
NYU Center for Data Science @nyudatascience.bsky.social · 03/06/2026
CDS Assistant Professor Mengye Ren (@mengyer.bsky.social) argues in a new paper that AI selfhood requires continual learning. Today’s LLMs wake from amnesia each session and read a diary of a past self — never extending themselves through new experience. nyudatascience.medium.com/to-have-a-se...
nyudatascience.medium.com
To Have a Self, an AI Must Live a Life
Every copy of a large language model begins each conversation identical to every other copy. They share the same weights and the same…
072
Reposted by agentic learning ai lab
Mengye Ren @mengyer.bsky.social · 19/05/2026
What does it mean to create a new concept rather than retrieve a familiar one? I propose that creativity is what's unfamiliar at first but quickly learnable by an adaptive observer, and show that meta-learning through a frozen Diffusion model produces stylistic & conceptual creations.
141
Reposted by agentic learning ai lab
NYU Center for Data Science @nyudatascience.bsky.social · 06/05/2026
AI agents often struggle to plan movements because their internal representations of the physical world can be overly tangled. CDS PhD student Ying Wang shows how straightening these pathways improves AI navigation. Accepted to ICML 2026. nyudatascience.medium.com/improving-wo... 1/2
nyudatascience.medium.com
Improving World Models: A Neuroscience-Inspired Approach to Latent Planning
Humans instinctively map out the physical consequences of their actions before taking them, seamlessly predicting that a dropped glass will…
142
Reposted by agentic learning ai lab
agentic learning ai lab @agenticlearning.ai · 24/04/2026
Agentic Learning AI Lab is at #ICLR2026, come check out our work! @mengyer.bsky.social @choang.bsky.social @jacklu-me.bsky.social Frank Wu🧵
172
agentic learning ai lab @agenticlearning.ai · 24/04/2026
Agentic Learning AI Lab is at #ICLR2026, come check out our work! @mengyer.bsky.social @choang.bsky.social @jacklu-me.bsky.social Frank Wu🧵
172
Reposted by agentic learning ai lab
Mengye Ren @mengyer.bsky.social · 08/04/2026
New preprint: The Self Requires Learning. Self-consciousness requires continual learning + world-modeling. I introduce "bounded integration" to connect perspective, identity, and self-representation — and diagnose what current AI systems have and lack. Full paper: mengyeren.com/research/202...
191
agentic learning ai lab @agenticlearning.ai · 17/03/2026
Latent trajectories from pretrained models are curved and zigzagged. We add a simple straightening objective that makes the latent transitions smooth and trajectories straightened. Check out our latest research by @yingwww.bsky.social @yann-lecun.bsky.social @mengyer.bsky.social and colleagues!
031
Reposted by agentic learning ai lab
Mengye Ren @mengyer.bsky.social · 19/02/2026
Sharing my thoughts on Moltbook in a recent interview by The Independent.
071
agentic learning ai lab @agenticlearning.ai · 30/01/2026
Verifiers are increasingly being used today in RL to provide rewards. We did a systematic study on when it is the best to use LLMs to verify solutions. Check out the blog post below to learn more.
031
agentic learning ai lab @agenticlearning.ai · 19/12/2025
Babies learn to perceive the world and develop object and motion recognition in the early stages of life. Can a network bootstrap this understanding just by watching video? Check out the new blog post featuring our latest research on the Midway Network.
010
agentic learning ai lab @agenticlearning.ai · 12/12/2025
Excited to share our new research on local RL without backprop!
021
agentic learning ai lab @agenticlearning.ai · 10/12/2025
Lab gathering at #NeurIPS2025. Proud of this year’s work and excited about the ideas we’re building toward next!
041
Reposted by agentic learning ai lab
Christian Wolf @chriswolfvision.bsky.social · 27/10/2025
Midway networks are cool: representation learning of motion and reconstruction jointly. I see similar motivation in V-JEPA 2 "AC", but I really like the execution here: - hierarchical, - backwards features with cross-attention. arxiv.org/abs/2510.05558 C. Hoang, @mengyer.bsky.social NYU
081
agentic learning ai lab @agenticlearning.ai · 20/04/2025
Check out our latest paper on representation learning from naturalistic videos →
020
Reposted by agentic learning ai lab
NYU Center for Data Science @nyudatascience.bsky.social · 22/01/2025
New research by CDS MS student Amelia (Hui) Dai, PhD student Ryan Teehan, and Asst. Prof. Mengye Ren (@mengyer.bsky.social) shows that models’ accuracy on current events drops 20% over time—even when given the source articles. Presented at #NeurIPS2024. nyudatascience.medium.com/language-mod...
nyudatascience.medium.com
Language Models’ Prediction of Current Events Degrades Over Time, Even With Latest Information
Language models lose accuracy on predicting events over time, even with access to up-to-date information.
082