ROSS: Relearning from Self-Generated Rollouts through Selective Supervision
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/openai/codex
Sources
- Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking
- RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
- daVinci-Env: Open SWE Environment Synthesis at Scale
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
- Process Reward Models That Think
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
- Step Rejection Fine-Tuning: A Practical Distillation Recipe
- Kimi K3: Open Frontier Intelligence
- OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
- MiMo-V2-Flash Technical Report
- Qwen3 Technical Report
- Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
- GLM-5: from Vibe Coding to Agentic Engineering
- Group Sequence Policy Optimization
- SWE-Prime: Fewer Trajectories, Better Performance
- RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks