arXiv:2603. 03538v4 Announce Type: replace Abstract: Large Language Models (LLMs) using chain-of-thought reasoning have demonstrated great potential for solving complex reasoning and planning tasks.
arXiv:2609.38409v1 Announce Type: new Abstract: Recent progress in large language model reasoning has been driven by benchmarks and reinforcement learning environments with automatically verifiable r...
arXiv:2605. 03862v4 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful to the model that consumes it.
arXiv:2605. 12519v2 Announce Type: replace-cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge.
The paper introduces a neuro‑symbolic framework for scientific reasoning that separates symbolic validity and semantic groundedness. A deterministic symbolic verifier acts as a hard filter to guarantee syntactic and arithmetic correctness, while a Process Reward Model (PRM) is trained on verifier‑accepted steps to assess contextual grounding. The authors propose Counterfactual Symbolic Perturbation (CSP) to generate hard negative examples that pass the verifier but are logically flawed, enabling efficient PRM training and a verifier‑first constrained search at inference.
arXiv:2609.30572v1 Announce Type: cross Abstract: Large language models are often post-trained on expert demonstrations using cross-entropy (CE), even when the downstream objective is not to imitate...
arXiv:2606. 01281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs).
arXiv:2604. 11996v2 Announce Type: replace-cross Abstract: Should we trust Large Language Models (LLMs) with high accuracy?
The paper investigates whether the high costs of training chain-of-thought reasoning models can be reduced through algorithmic design. It introduces an autocurriculum approach that lets the model select which problems to focus on during training, showing that this method provably improves both supervised fine‑tuning and reinforcement learning. For supervised fine‑tuning, autocurriculum requires exponentially fewer reasoning demonstrations by targeting prompts where the model struggles, while for reinforcement learning it decouples computational cost from the quality of the reference model, making the burn‑in cost nearly independent of target accuracy.
arXiv:2511. 21667v4 Announce Type: replace Abstract: Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers.
arXiv:2606. 01599v1 Announce Type: new Abstract: Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals.
The paper reports that in on‑policy distillation for large language models, reasoning performance can be improved by supervising only a tiny fraction of generated tokens—sometimes just one or two tokens per reasoning trajectory, about 0.05% of all tokens. This sparse supervision consistently matches or exceeds full‑token training across nine teacher‑student setups on mathematical reasoning, and is also validated on coding reasoning, Llama models, and PPO‑based reinforcement learning with verifiable reward. The findings suggest that effective post‑training does not require token‑intensive supervision and may align more closely with natural learning processes that focus on critical reasoning steps.
The paper introduces a new approach to distill reasoning abilities from large language models (LLMs) into smaller student models by framing the task as a constrained reinforcement learning problem. It enforces a worst‑case constraint on the teacher’s log‑likelihood for every prefix of the reasoning chain, avoiding reward hacking and excessive teacher regularization. Experiments on mathematical reasoning and code generation show that this method improves the balance between accuracy and fidelity, achieving the highest rigorous reasoning success rate among evaluated settings.