« OrderGrad: Optimization Beyond the Mean with Policy Gradient Estimation by Order Statistics » Most RL optimizes the average reward, but deployment often cares about the best sample, the worst tail, the median, CVaR, or
RESEARCH
-
OPRD: On-Policy Distillation of Teacher Representations Before LM Head
By
–
"OPRD: On-Policy Representation Distillation" On-policy distillation usually matches teacher and student only at the token probability level, throwing away the teacher’s hidden states. This paper moves the loss before the LM head, aligning student and teacher representations on
-
Pedro’s earlier insight on Gato and universal AI imitation
By
–
Thanks for asking. Pedro pointed out issue much earlier when I was working on General AgenT One — Gato https://
arxiv.org/abs/2205.06175 and wrote about it https://
arxiv.org/abs/2110.10819 Then Pedro came up with this brilliant theoretical insight: https://
adaptiveagents.org/universal_ai_a
s_imitation
… And we -
AI crosses the threshold of recursive self-improvement
By
–
AI has just crossed a threshold: recursive self-improvement. Models write the code that trains them, discover the algorithms that will make them better, design the chips that run them… The machine improves the machine, which will improve the machine.
-
Request for precise explanation of causal training of world models
By
–
Could you please be more precise. Could you show us precisely how world models are trained causally. Thanks
-
Better models help researchers build better models faster
By
–
The biggest misconception about AI progress is that it's only about bigger models.
Anthropic's data suggests something different:
Better models are helping researchers build better models faster.
That's a very different kind of scaling law.
#AI #Claude #MachineLearning -
Assessing AI Doctors and Their Future in Medicine
By
–
How good are ‘#AI doctors’ — and will they take over medicine?
by Mariana Lenharo @Nature Learn more: https://
bit.ly/4vyeeuh #MedTech #HealthTech #Tech #TechForGood -
Top AI Papers of the Week: May 31 – June 7
By
–
The Top AI Papers of the Week (May 31 – June 7) – LEAP
– AutoLab
– Learn From Your Own Latents
– Reusable Context Engineering
– Self-Revising Discovery Systems
– Scaling Laws for Agent Harnesses
– Disentangling Agent Self-Evolution Read on for more: -
Microsoft Makes Agent Skills Self-Evolving
By
–
Handwritten skills are dead. Microsoft just taught them to self-evolve.
— AlphaSignal (@AlphaSignalAI) 7 juin 2026
Most agent skill docs are handwritten and brittle. They rarely improve once shipped.
Microsoft Research just released a paper fixing this.
It treats the skill file as a frozen agent's trainable state. A… pic.twitter.com/wG1DsD353jHandwritten skills are obsolete. Microsoft has now enabled them to self-evolve. Most agent skill documents are manually written and fragile. They rarely improve after deployment. Microsoft Research has just published a paper addressing this issue. It treats the skill file as a trainable state of a frozen agent.
-
Repo2RLEnv turns GitHub repos into RL training environments
By
–
Turn any GitHub repo into an RL training environment!
— Sumanth (@Sumanth_077) 7 juin 2026
Repo2RLEnv is a new open-source tool from HuggingFace that synthesizes verifiable RL training data from any GitHub repository. Point it at any repo and it automatically generates tasks, verifies them, and pushes datasets… https://t.co/VXqSNNcVNp pic.twitter.com/p0zmmycsZSTurn any GitHub repo into an RL training environment! Repo2RLEnv is a new open-source tool from HuggingFace that synthesizes verifiable RL training data from any GitHub repository. Point it at any repo and it automatically generates tasks, verifies them, and pushes datasets