arXiv:2510. 18814v4 Announce Type: replace-cross Abstract: Can language models improve their reasoning performance without external rewards, using only their own sampled responses for training?
arXiv:2606. 17803v1 Announce Type: new Abstract: Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process.
arXiv:2605.06165v2 Announce Type: replace Abstract: As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contribut...
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:2604. 13356v3 Announce Type: replace-cross Abstract: Mechanisms for continued self-improvement of language models without external supervision remain an open challenge.
arXiv:2607. 06974v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most existing works treat each problem in isolation.
The paper demonstrates that fine‑tuning reasoning models to predict their own confidence at intermediate steps—using only 600 self‑supervised examples—substantially improves inference efficiency. Without adding any explicit stopping or length penalties, the models generate up to 25 % fewer tokens while maintaining accuracy on mathematical, scientific, and coding benchmarks across several architectures. The study finds that confidence supervision preserves the models’ high‑level reasoning structure rather than merely suppressing specific behaviors.
arXiv:2601. 20379v2 Announce Type: replace Abstract: Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption.
arXiv:2507.21931v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks....
Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most existing works treat each problem in isolation. When problems arrive sequentially, accumulating reusable experience across them can further improve performance.
arXiv:2606. 19327v1 Announce Type: new Abstract: Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards.
Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often relies on chain-of-thought annotations that are expensive to obtain and may themselves be noisy, incomplete, or partially incorrect; even when the final solution is correct, an imperfect rationale can interfere with learning.
AdaR is a framework designed to enhance large language models (LLMs) with adaptive reasoning for mathematical tasks. It identifies and mitigates spurious reasoning—where models rely on superficial correlations—by generating logically equivalent queries and training with Reinforcement Learning with Verifiable Rewards (RLVR) to penalize incorrect logic and promote adaptive logic. The approach includes extracting problem‑solving logic, executing code to verify answers, and applying sanity checks, resulting in significant gains in mathematical reasoning performance and improved data efficiency.