arXiv:2510.01581v2 Announce Type: replace-cross Abstract: Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in l...
arXiv:2505. 24273v2 Announce Type: replace Abstract: Recent advancements in large language models (LLMs) suggest that reinforcement learning (RL) effectively internalizes search strategies, yielding significant improvements on challenging reasoning tasks through extended chains of thought.
arXiv:2508. 09883v2 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving.
The paper studies how the distribution of information across chain‑of‑thought steps—measured by LP variance and Caveman compression ratio—relates to answer correctness in large language models. Across six model sizes, two training paradigms, and 60 GSM8K problems, it finds that lower LP variance predicts accuracy in supervised fine‑tuned models but not in reinforcement‑learning distilled ones, that models prefer more complex distributions, and that steering density at inference time harms accuracy while pre‑generation nudging and a new Entropy‑Gated Density Routing method improve it. The work demonstrates that natural density patterns are functionally important for reasoning and offers practical techniques to enhance performance.
arXiv:2510. 19990v2 Announce Type: replace Abstract: The reasoning paradigm, where language models reason before answering, has enabled breakthroughs on tasks such as mathematical problem-solving.
The paper introduces Multi-Level Reasoning (MLR), a two-level stochastic framework that separates long chain-of-thought generation into a high-level planner producing structured step descriptors and a low-level executor generating detailed reasoning. MLR replaces single-policy reinforcement learning with an iterative Step‑DPO preference optimization that uses Twisted Sequential Monte Carlo for scalable, stepwise supervision, improving training stability and accuracy. Experiments on math, science, and logic benchmarks show that MLR outperforms both supervised fine‑tuning and strong RL baselines while maintaining robustness over extended reasoning horizons.
arXiv:2608.28600v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance on mathematical reasoning benchmarks, yet the mathematically meaningful skills underlying their...
arXiv:2603.00889v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, largely enabled by supervised fine-tuning (SFT)- and reinforce...
arXiv:2606. 07108v1 Announce Type: new Abstract: Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from inefficiencies due to redundant reasoning, known as "overthinking".
arXiv:2603.00578v2 Announce Type: replace-cross Abstract: Long chain-of-thought~(CoT) reasoning improves the problem-solving capability of large reasoning models~(LRMs), but often incurs substantial...
Ladders-of-Thought (LoT) is a framework that enhances reasoning in small- to mid-scale large language models by automatically generating easier variants of reasoning problems and organizing them into difficulty buckets. It uses a self‑evolving bandit scheduler to adaptively allocate training, improving performance across math and multi‑hop reasoning tasks on 1–8 B models. LoT achieves significant gains (e.g., +32 pp on AddSub, +16 pp on QASC) and converges faster than staged curricula.
The paper introduces Stitching Noisy Diffusion Thoughts, a self‑consistency framework that transforms low‑cost diffusion‑sampled reasoning into a reusable pool of step‑level candidates. By sampling many diverse trajectories with a masked diffusion language model, scoring each intermediate step with a process reward model, and stitching the highest‑quality steps across trajectories, the method recomputes only the final answer, separating exploration from evaluation. Experiments on math reasoning benchmarks show that step‑level recombination improves accuracy by up to 23.8% on six tasks while reducing latency by up to 1.8× compared to traditional diffusion models and unified architectures.