Reward Hacking in Rubric-Based Reinforcement Learning
Paper • 2605.12474 • Published • 2
M Saad Salman
MSS444
AI & ML interests
None yet
Recent Activity
upvoted a paper about 6 hours ago
Reward Hacking in Rubric-Based Reinforcement Learning upvoted a paper about 6 hours ago
Do not copy and paste! Rewriting strategies for code retrieval upvoted a paper about 6 hours ago
Continual Harness: Online Adaptation for Self-Improving Foundation AgentsOrganizations
None yet
upvoted 5
papers about 6 hours ago
Do not copy and paste! Rewriting strategies for code retrieval
Paper • 2605.08299 • Published • 4
Continual Harness: Online Adaptation for Self-Improving Foundation Agents
Paper • 2605.09998 • Published • 9
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
Paper • 2605.12483 • Published • 7
Teaching Language Models to Think in Code
Paper • 2605.07237 • Published • 17
upvoted a paper 2 days ago
upvoted 5
papers 5 days ago
AI Co-Mathematician: Accelerating Mathematicians with Agentic AI
Paper • 2605.06651 • Published • 13
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Paper • 2605.06130 • Published • 94
SkillOS: Learning Skill Curation for Self-Evolving Agents
Paper • 2605.06614 • Published • 38
Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes
Paper • 2605.05724 • Published • 14
Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration
Paper • 2605.05566 • Published • 35
upvoted 9
papers 9 days ago
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
Paper • 2604.26779 • Published • 13
Large Language Models Explore by Latent Distilling
Paper • 2604.24927 • Published • 74
Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
Paper • 2604.24952 • Published • 6
Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models
Paper • 2604.27251 • Published • 8
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
Paper • 2604.24954 • Published • 22
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
Paper • 2604.27039 • Published • 24
Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
Paper • 2604.28158 • Published • 47
Efficient Training on Multiple Consumer GPUs with RoundPipe
Paper • 2604.27085 • Published • 40
Co-Evolving Policy Distillation
Paper • 2604.27083 • Published • 64