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.
By Xun Lu, Shumeng Yang, Xinrui Wang, Songjun Tu, Linjing Li, Daniel Dajun Zeng
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...
By Jason Ken Adhinarta, Raina Wu, Ashutosh Sharma, Avinash Balakrishnan, Rameswar Panda, Polina Golland, Yoon Kim, Zhang-Wei Hong
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...
By Jiaxuan Wang, Xuan Ouyang, Zhiyu Chen, Yulan Hu, Lan-Zhe Guo
arXiv:2607. 11506v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) optimizes LLMs using sparse verifiable final-answer rewards.
By Xiaojian Liu, Han Xu, Jianqiang Xia, Zhixuan Li, Ke Xu, Yiwei Dai, Xinran Chen, Changwo Wu, Yuchen Li
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.
By Minghua He, Lingzhe Zhang, Yuan Liu, Xiao Zhou, Aiwei Liu
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.
By Dhruv Saini, Rohan Pandey
arXiv:2607. 11505v2 Announce Type: replace-cross Abstract: Post-training for large language models typically couples policy exploration with model optimization, hindering the reuse of high-reward behaviors from policy exploration.
By Daocheng Fu, Rong Wu, Yu Yang, Jianbiao Mei, Licheng Wen, Pinlong Cai, Xuemeng Yang, Yong Liu, Botian Shi, Yu Qiao
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
By Wonjoong Kim, Yeonjun In, Sangwu Park, Dongha Lee, Chanyoung Park
arXiv:2607. 05199v1 Announce Type: new Abstract: Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows.
By Raj Jaiswal, Dhruv Jain, Rishabh Dhawan, Sree Krishna Uppalapati, Shin'ichi Satoh, Tanuja Ganu, Rajiv Ratn Shah
The paper introduces EvoResearcher, a training‑free, inference‑time protocol that enables a frozen large language model to perform cost‑bounded self‑reflection and early stopping. By iterating through generate → self‑critique → revise steps until a maximum depth or a CONFIRMED sentinel is reached, the model can self‑verify its answers within a strict compute budget. The protocol incorporates four self‑reflective meta‑reward components—correctness, efficiency, reflection depth, and tool‑call diversity—implemented as prompt‑level mechanisms, and is validated on Big‑Bench Hard, GSM8K, and MATH benchmarks, achieving comparable accuracy while terminating 82‑88% of items early with only about 2.1 generations per question.
By Wei Yu, Suxing Liu, Minjie Yu, Jiahao Wang, Zhijian Zheng, Haocheng Deng, Bing Li
arXiv:2606. 03620v1 Announce Type: cross Abstract: Self-distilled policy optimization (SDPO) has become a popular paradigm for LLM post-training, where a model learns from its own predictions conditioned on privileged information.
By Ke Wang, Yuning Wu, Haoran Liu, Chaoqun Jia, Devin Chen, Kai Wei
arXiv:2608. 02087v2 Announce Type: replace Abstract: Post-training Large Language Models (LLMs) with Reinforcement Learning (RL) has become an important tool for improving model capabilities, but the LLM action-space structure introduces challenges distinct from classical RL, with implications for inducing exploration.
By Jim Dilkes, Vahid Yazdanpanah, Sebastian Stein