Co-Evolving Policy Distillation paper: https://
huggingface.co/papers/2604.27
083
…
AGENTS
-
Co-Evolving Policy Distillation New AI Research Paper
By
–
-
Agent-Native Research Artifacts: The Last Human-Written Paper
By
–
The Last Human-Written Paper
— AK (@_akhaliq) 1 mai 2026
Agent-Native Research Artifacts
paper: https://t.co/cju1daCYH5 pic.twitter.com/tx9FpBDu22The Last Human-Written Paper Agent-Native Research Artifacts paper: https://
huggingface.co/papers/2604.24
658
… -
Automating Engineering Pipelines with AI Agents
By
–
12- Ce que ça permet concrètement •code review automatique
•tri des bugs
•issue → PR automatique
•travail junior compressé en “écriture d’issue” pipeline d’ingénierie entièrement automatisé -
Automating GitHub Actions with Claude for autonomous code development
By
–
9- Démo GitHub Action (impressionnant) GitHub Action = robot d’automatisation
Exemple réel : 1- Créer une demande (issue)
2- Claude crée une todo list
3- Claude modifie les fichiers
4- Claude propose une PR L’humain ne touche pas au code
écrire la demande = -
Using system prompts to customize AI behavior and create agents
By
–
8- –system-prompt pour changer la personnalité Tu peux changer le comportement de l’IA facilement : • “parle comme un pirate” (fun)
• “respecte les règles internes du client” (pro) Tu peux créer des agents personnalisés pour chaque client -
Explaining the Claude Code SDK for Autonomous AI Agents
By
–
1- C’est quoi le Claude Code SDK ? (99 % des gens ne savent pas) La plupart des développeurs utilisent Claude via le chat et s’arrêtent là Mais avec le SDK (outil pour appeler Claude depuis ton programme), tu peux lancer un agent Claude Code (une IA autonome qui travaille) en
-
Aletheia AI Agent Tackles 10th Mathematics Paper Autonomously
By
–
Looking forward to speaking at this tomorrow! And maybe reveal a bit what the 10th paper that #Aletheia has helped mathematicians (autonomously) tackle is 🙂
-
Using Independent Agents to Grade With Engineer-Based Rubric
By
–
i have a rubric based on how two Senior Engineers actually solved the problem, and i use a few independent agents to grade
-
Recursive Multi-Agent LLMs Collaborate in Latent Space
By
–
“Recursive Multi-Agent Systems” Many multi-agent LLM systems rely on agents passing text back and forth. This paper argues for a different approach where it makes agents recur together in latent space. So agents refine latent thoughts, pass hidden states across one another,