Article
One sandbox per rollout, or how labs run RL for agents in 2026
sergiopaniego
• • 10
Gibran Iqbal
Jibbscript
AI & ML interests
None yet
Recent Activity
liked a model about 20 hours ago
nomic-ai/nomic-embed-text-v1.5 liked a model about 20 hours ago
nvidia/Nemotron-3-Embed-8B-BF16 liked a model about 20 hours ago
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2Organizations
upvoted an article 1 day ago
upvoted 5
papers 1 day ago
StepAudio 3 Gen Technical Report
Paper • 2609.12945 • Published • 86
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
Paper • 2609.11682 • Published • 39
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
Paper • 2609.08418 • Published • 144
Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training
Paper • 2609.15051 • Published • 9
Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
Paper • 2609.11977 • Published • 98
upvoted a paper 4 days ago
upvoted a collection 4 days ago
upvoted an article 4 days ago
Article
NeoMME: an efficient Multimodal-native and Multilingual Encoder
Hcompany
• • 103 upvoted a collection 6 days ago
upvoted 3
papers 7 days ago
upvoted an article 12 days ago
Article
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
- +1
iamleonie, burtenshaw, sergiopaniego
• • 118 upvoted an article 13 days ago
Article
Training a coding model to paint watercolours with TRL and OpenEnv
sergiopaniego
• • 68 upvoted a collection 13 days ago
upvoted a paper 18 days ago
upvoted 3
papers 29 days ago
Agentic Transaction: Towards ACID-Compliant Agent Systems
Paper • 2608.13900 • Published • 27
How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks
Paper • 2608.14905 • Published • 31
Latent On-Policy Self-Distillation
Paper • 2608.13040 • Published • 26