The paper argues that pattern recognition and step‑by‑step reasoning lie on a spectrum, with large language models (LLMs) learning the latter when the next token depends on only a few preceding tokens. It formalises reasoning traces as paths on a De Bruijn graph, showing that the number of edges is far smaller than the number of possible traces, making step‑by‑step reasoning sample‑efficient. Experiments fine‑tuning Qwen2.5‑1.5B‑Instruct demonstrate that a moderate density of states balances accuracy and robustness, and that real‑world models like Qwen3 retain most of their performance even when attention is limited to a small sliding window.
By Amrut Nadgir, Pratik Chaudhari, Vijay Balasubramanian
arXiv:2610.15501v1 Announce Type: new
Abstract: Large language models make decisions through parallel prefill and sequential decoding. Although effective, this approach incurs decoding costs and does...
By Ziyi Chen, Yan Zhang, Jianhui Wei, Jianing Yin, Daoan Zhang
arXiv:2604. 10827v2 Announce Type: replace Abstract: Compute scaling for LLM reasoning trades off exploring solution approaches (\emph{breadth}) against refining promising ones (\emph{depth}), yet why a given trade-off works, and why it often fails to transfer across models, remains unclear.
By Moulik Choraria, Argyrios Gerogiannis, Anirban Das, Supriyo Chakraborty, Sourya Basu, Sambit Sahu, Lav R. Varshney
arXiv:2608.30413v1 Announce Type: new
Abstract: Defeasible reasoning is a type of reasoning where inferences are drawn from plausible current evidence, but can be retracted upon the introduction of n...
By Jayanta Sadhu, Sayem Shahad, Kenneth Marino
Defeasible reasoning is a type of reasoning where inferences are drawn from plausible current evidence, but can be retracted upon the introduction of newer evidence. Although recent studies have exami...
Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins. These models are built through post-training, yet how each stage shapes reasoning and generalization remains poorly understood.
Supervised fine-tuning (SFT) on a small, high-quality set of long reasoning traces is an effective approach for eliciting strong reasoning capabilities in Large Language Models (LLMs). However, existing methods for curating high-quality SFT data rely heavily on strong reasoning models to filter examples based on diversity and difficulty, making the curation process costly while often yielding suboptimal data quality.
arXiv:2605.13165v2 Announce Type: replace
Abstract: Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking. This inefficiency is espe...
By Chenjun Xu, Zhennan Zhou, Zhan Su, Bill Howe, Lucy Lu Wang, Bingbing Wen
BoundaryEvo introduces a two‑stage data‑model co‑evolution framework for distilling long‑chain reasoning from large teacher models into small language models. First, Capability Priming distills a small set of teacher trajectories to give the student an initial reasoning baseline. Then, Capability‑Boundary Co‑Evolution iteratively selects questions the student has not mastered but the teacher can solve, updating the training data as the student’s capability grows. With only 1,000 examples, BoundaryEvo improves Qwen3.5‑4B accuracy from 62.9 % to 75.3 % on IMO‑AnswerBench and from 26.8 % to 46.0 % on AMO‑Bench, outperforming static and dynamic baselines across 11 benchmarks.
By Jiaming Su, Suorong Yang, Xudong Li, Tengchao Yang, Peng Ye
arXiv:2602.21189v3 Announce Type: replace-cross
Abstract: Pass@$k$ is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, an...
By Anas Barakat, Souradip Chakraborty, Khushbu Pahwa, Amrit Singh Bedi
arXiv:2607. 20500v1 Announce Type: new Abstract: Large Language Models (LLMs) perform strongly on well-specified reasoning tasks with a feasible answer.
By Sizhe Tang, Guangyu Jiang, Yu Li, Rongqian Chen, Ioannis G. Kevrekidis, Tian Lan
The paper investigates Evolution Strategies (ES) as a memory‑efficient post‑training method for large language model (LLM) reasoning. It demonstrates that ES outperforms Group Relative Policy Optimization (GRPO) by achieving broader reasoning coverage, improving Pass@K metrics, and avoiding entropy collapse. The study also reveals that ES’s performance gains stem from sparse, high‑magnitude parameter updates, do not cause catastrophic forgetting, and can be combined with GRPO in a sequential training strategy.
By Yunpeng Ba, Zhi Zheng, Yue Xie, Jiaqing Li, Xialiang Tong, Tao Zhong, Mingxuan Yuan, Zhichao Lu, Xuyang Wu, Zhenkun Wang