An early mistake in the generated reasoning can constrain all subsequent reasoning. Repeated-generation methods, like MCMC-based approaches, attempt to improve output quality by sampling multiple gene...
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.
arXiv:2601. 02880v2 Announce Type: replace Abstract: Every existing inference-time reasoning framework discards all failure context at problem boundaries, leaving a model solving problem 500 no wiser than it was on problem 1.
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.
arXiv:2608.28704v1 Announce Type: new Abstract: AI agents increasingly perform long-term reasoning, planning, tool use, memory integration, and autonomous decision making, yet erroneous intermediate...
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...
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:2607. 21453v1 Announce Type: new Abstract: Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks.
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.
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...
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.