arXiv:2610.19561v1 Announce Type: new Abstract: An early mistake in the generated reasoning can constrain all subsequent reasoning. Repeated-generation methods, like MCMC-based approaches, attempt to...
Selective Regenerative Decoding (SRD) is a new inference-time decoding method that improves large language model reasoning by allowing segment-level intervention on candidate trajectories. Instead of discarding or keeping entire trajectories, SRD selectively refines only the degraded suffix while preserving useful prefixes, leading to higher expected trajectory quality and better sample efficiency. Experiments on MATH500, GPQA Diamond, HotpotQA, and AlpacaEval show that SRD matches Best-of-N accuracy with fewer generated tokens and outperforms speculative rejection in low‑compute settings.
arXiv:2606. 00305v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) improves large language model reasoning by training a student model on trajectories sampled from its own policy under teacher supervision.
Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generated via uncontrolled sampling, it provides no diagnostic insight into the model's specific errors or corrective guidance for its individual failure patterns.
arXiv:2606. 18844v1 Announce Type: new Abstract: Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution.
The paper introduces Stable-MM-R1, a framework that stabilizes reinforcement learning for multimodal reasoning by addressing training instability and entropy collapse. It proposes Potential‑Aware Query Mining (PAQM) to filter data toward high‑potential samples and Hybrid Stratified Replay (HSR) to restructure batches using path entropy and reward stratification, reusing stability anchors and hard negatives. The method demonstrates superior performance on complex reasoning tasks compared to strong baselines.
The paper introduces Adaptive Reference Guidance (ARG), a method that balances using a verified reference solution with free generation in trajectory rollouts for reasoning reinforcement learning. ARG selects a prefix of the reference to guide the model, continuing from it only if the resulting trajectory passes verification, otherwise falling back to the reference. Experiments on Qwen3-4B and Qwen3-8B across five mathematical reasoning benchmarks demonstrate that ARG achieves the highest aggregate pass@12 while maintaining competitive average sampled accuracy.
arXiv:2605.23074v2 Announce Type: replace Abstract: Large Reasoning Language Models (LRMs) tackle complex tasks through test-time scaling, generating long-form Chain-of-Thought (CoT) trajectories dur...
arXiv:2602. 02244v3 Announce Type: replace Abstract: The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes overconfidence and reduces generation diversity, leaving RL with a narrowed solution space to explore.
arXiv:2609.33149v2 Announce Type: replace Abstract: A common principle of effective learning is to practice material that is neither already mastered nor too difficult to permit progress. We ask how...
Reflective Recovery is a self‑supervised method that turns failed reasoning attempts into training data, enabling large language models to learn how to correct mistakes during inference. By extracting initial segments of erroneous trajectories and using them as prompts, the approach teaches models to recognize and recover from errors without external critics. Experiments show significant accuracy gains on benchmarks such as AIME 2025 and Minerva, and the method overcomes the scaling collapse problem, fostering emergent self‑correction behaviors.
arXiv:2606. 09932v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training.