arXiv:2601. 15158v4 Announce Type: replace-cross Abstract: Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought).
arXiv:2604. 11912v2 Announce Type: replace-cross Abstract: While next-token prediction (NTP) has been the standard objective for training language models, it often struggles to capture global structure in reasoning tasks.
arXiv:2606. 00183v1 Announce Type: cross Abstract: Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives.
arXiv:2607. 26119v1 Announce Type: new Abstract: Large reasoning models trained via reinforcement learning (RL) have been increasingly shown to outperform their supervised fine-tuned (SFT) counterparts on mathematical reasoning tasks; Yet the mechanistic basis for this advantage remains unclear.
arXiv:2604. 07822v2 Announce Type: replace-cross Abstract: We study implicit reasoning, i.
Recent advances in large language models (LLMs) have demonstrated that reinforcement fine-tuning of pretrained base models can lead to significant gains in reasoning performance at inference time. In this work, we theoretically analyze why reinforcement fine-tuning induces better reasoning ability than purely supervised fine-tuning (SFT) methods.
The paper introduces a dependency‑graph framework to formalize compositional reasoning in language models, defining three increasing levels of compositionality. Using data‑structure tasks with deterministic rewards, the authors observe a consistent asymmetry: training on decomposed skills does not reliably transfer to composed tasks, whereas training on composed tasks transfers more readily to decomposed ones. They provide a theoretical explanation for this asymmetry and evaluate its effects under length extrapolation, structural distribution shift, and transfer to unseen skills, concluding with a pilot study on real‑world tool‑calling benchmarks that suggests the phenomenon extends to practical settings.
arXiv:2602. 14872v3 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models.
arXiv:2603.21676v2 Announce Type: replace-cross Abstract: Standard Transformers have a fixed computational depth, limiting their ability to generalize to tasks that require variable-depth reasoning....
arXiv:2602. 07832v3 Announce Type: replace-cross Abstract: Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking.
arXiv:2607. 16205v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has emerged as a standard approach for enhancing reasoning in large language models, which typically optimizes the policy by contrasting multiple self generated rollouts.
arXiv:2607. 11875v1 Announce Type: cross Abstract: We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models.
arXiv:2509. 18930v3 Announce Type: replace-cross Abstract: Neural algorithmic reasoning (NAR) is a paradigm that trains neural networks to execute classic algorithms by supervised learning.