arXiv Machine Learning
Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 16
Learning to Reason with Selective Internal Feedback
The paper introduces SIF, a reinforcement learning technique that uses selective internal feedback to improve language models’ reasoning without external verifiers. SIF constructs comparative rewards by comparing token‑level self‑certainty across multiple windows and peers, rewarding only when both voting levels agree, and applies sample and group‑level filtering to decide which responses influence policy updates. Experiments on three backbone models across 12 mathematical and scientific benchmarks show that SIF’s final checkpoints outperform the best‑validation checkpoints of Intuitor and Vigor, achieving a 4.71‑point accuracy gain on Qwen2.5‑Math‑1.5B and maintaining accuracy during continued optimization with minimal test‑time rollouts.
arXiv AI
Oct 15
Does self-distillation improve reasoning?
arXiv:2610.18613v1 Announce Type: cross Abstract: Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as corr...
arXiv AI
Oct 1
STEPS: Selective On-Policy Self-Distillation for Reasoning
arXiv:2605.10194v2 Announce Type: replace Abstract: On-policy self-distillation (OPSD) uses a model as its own teacher under privileged context, providing token-level supervision on the model's own r...
arXiv Machine Learning
Jul 14
SCOPE-RL: Optimizing Reasoning Paths Before and After Success
arXiv:2607. 11506v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) optimizes LLMs using sparse verifiable final-answer rewards.
arXiv Machine Learning
Sep 16
GrowMTP: Can RL Grow Its Own Draft Head?
GrowMTP is a method that trains a draft head entirely within the reinforcement learning (RL) loop, using supervision from the RL verification step and a rollout distribution that is narrower than pretraining. By detaching draft‑head updates from the policy backbone, it enables online training of the draft head from scratch. Experiments on Qwen3‑4B, MiMo‑7B‑SFT, and Qwen3.5‑4B‑Base show rollout speedups ranging from 1.36× to 2.13× and overall end‑to‑end speedups from 1.20× to 1.60×, making it a modular acceleration component for RL frameworks lacking pretrained draft heads.
arXiv AI
Jun 2
ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks
arXiv:2606. 01080v1 Announce Type: cross Abstract: Large language models often improve on difficult tasks by spending inference-time compute on a reasoning trace before producing the final answer.