English
Related papers

Related papers: Think in Parallel, Answer as One: Logit Averaging …

200 papers

Large Reasoning Models (LRMs) allocate substantial inference-time compute to Chain-of-Thought (CoT) reasoning, improving performance on mathematics, scientific QA, and tool usage. However, this introduces overthinking: LRMs often reach a…

Computation and Language · Computer Science 2026-04-21 Sangjun Song , Minjae Oh , Seungkyu Lee , Sungmin Jo , Yohan Jo

Recent advances in large language models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated the effectiveness of test-time scaling, where extended reasoning processes substantially enhance model performance. Despite this, current…

Computation and Language · Computer Science 2025-03-26 Xiaoyu Tian , Sitong Zhao , Haotian Wang , Shuaiting Chen , Yunjie Ji , Yiping Peng , Han Zhao , Xiangang Li

Large Language Models (LLMs) have shown great potential in reasoning tasks through test-time scaling methods like self-consistency with majority voting. However, this approach often leads to diminishing returns in accuracy and high…

Machine Learning · Computer Science 2025-08-22 Yichao Fu , Xuewei Wang , Yuandong Tian , Jiawei Zhao

We revisit test-time scaling for language model reasoning and ask a fundamental question: at equal token budget and compute, is it better to run multiple independent chains in parallel, or to run fewer chains that iteratively refine through…

Machine Learning · Computer Science 2025-11-05 Aman Sharma , Paras Chopra

Parallel thinking has emerged as a promising paradigm for reasoning, yet it imposes significant computational burdens. Existing efficiency methods primarily rely on local, per-trajectory signals and lack principled mechanisms to exploit…

Computation and Language · Computer Science 2026-02-12 Tong Zheng , Chengsong Huang , Runpeng Dai , Yun He , Rui Liu , Xin Ni , Huiwen Bao , Kaishen Wang , Hongtu Zhu , Jiaxin Huang , Furong Huang , Heng Huang

Recent LLMs have significantly improved reasoning capabilities, primarily by including an explicit, lengthy Thinking process as part of generation. In this paper, we question whether this explicit thinking is necessary. Using the…

Artificial Intelligence · Computer Science 2025-04-15 Wenjie Ma , Jingxuan He , Charlie Snell , Tyler Griggs , Sewon Min , Matei Zaharia

Recent trends in test-time scaling for reasoning models (e.g., OpenAI o1, DeepSeek R1) have led to a popular belief that extending thinking traces using prompts like "Wait" or "Let me rethink" can improve performance. This raises a natural…

Large language models (LLMs) have shown increasing competence in solving mathematical reasoning problems. However, many open-source LLMs still struggle with errors in calculation and semantic understanding during intermediate reasoning…

Computation and Language · Computer Science 2024-12-18 Vernon Y. H. Toh , Deepanway Ghosal , Soujanya Poria

Large language models (LLMs) have demonstrated impressive reasoning capabilities by scaling test-time compute via long Chain-of-Thought (CoT). However, recent findings suggest that raw token counts are unreliable proxies for reasoning…

Computation and Language · Computer Science 2026-02-17 Wei-Lin Chen , Liqian Peng , Tian Tan , Chao Zhao , Blake JianHang Chen , Ziqian Lin , Alec Go , Yu Meng

In collaborative software development, program merging is the mechanism to integrate changes from multiple programmers. Merge algorithms in modern version control systems report a conflict when changes interfere textually. Merge conflicts…

Software Engineering · Computer Science 2021-09-08 Elizabeth Dinella , Todd Mytkowicz , Alexey Svyatkovskiy , Christian Bird , Mayur Naik , Shuvendu K. Lahiri

Test-time compute scaling is a primary axis for improving LLM reasoning. Existing methods primarily scale depth by extending a single reasoning trace. Scaling breadth by sampling multiple candidates in parallel is straightforward, but…

Artificial Intelligence · Computer Science 2026-05-19 Shang Zhou , Wenhao Chai , Kaiyuan Liu , Huanzhi Mao , Qiuyang Mang , Jingbo Shang

Large Reasoning Models (LRMs) excel at multi-step reasoning but often suffer from inefficient reasoning processes like overthinking and overshoot, where excessive or misdirected reasoning increases computational cost and degrades…

Artificial Intelligence · Computer Science 2026-01-19 Qianyue Wang , Jinwu Hu , Yufeng Wang , Huanxiang Lin , Bolin Chen , Zhiquan Wen , Yaofo Chen , Mingkui Tan

Large reasoning models (LRMs) can do complex reasoning via long chain-of-thought (CoT) involving cognitive strategies such as backtracking and self-correction. Recent studies suggest that some models inherently possess these long reasoning…

Computation and Language · Computer Science 2025-07-18 Yunxiang Zhang , Muhammad Khalifa , Lechen Zhang , Xin Liu , Ayoung Lee , Xinliang Frederick Zhang , Farima Fatahi Bayat , Lu Wang

Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling, offering competitive performance while naturally enabling a flexible decoding process. Specifically, dLLMs can generate tokens at arbitrary…

Computation and Language · Computer Science 2026-02-13 Sicheng Feng , Zigeng Chen , Xinyin Ma , Gongfan Fang , Xinchao Wang

Reasoning large language models (RLLMs) have recently demonstrated remarkable capabilities through structured and multi-step reasoning. While prior research has primarily focused on improving their training and inference strategies, their…

Computation and Language · Computer Science 2025-10-14 Haotian Wu , Bo Xu , Yao Shu , Menglin Yang , Chengwei Qin

Large language models (LLMs) have a substantial capacity for high-level analogical reasoning: reproducing patterns in linear text that occur in their training data (zero-shot evaluation) or in the provided context (few-shot in-context…

Computation and Language · Computer Science 2023-06-05 Batu Ozturkler , Nikolay Malkin , Zhen Wang , Nebojsa Jojic

The advent of test-time scaling in large language models (LLMs), exemplified by OpenAI's o1 series, has advanced reasoning capabilities by scaling computational resource allocation during inference. While successors like QwQ, Deepseek-R1…

Machine Learning · Computer Science 2025-03-04 Zhiyuan Zeng , Qinyuan Cheng , Zhangyue Yin , Yunhua Zhou , Xipeng Qiu

Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation required for strategic planning and self-correction. While RL…

Artificial Intelligence · Computer Science 2026-05-29 Yang He , Xiao Ding , Bibo Cai , Yufei Zhang , Kai Xiong , Zhouhao Sun , Bing Qin , Ting Liu

Scaling test-time compute brings substantial performance gains for large language models (LLMs). By sampling multiple answers and heuristically aggregate their answers (e.g., either through majority voting or using verifiers to rank the…

Computation and Language · Computer Science 2025-10-13 Jianing Qi , Xi Ye , Hao Tang , Zhigang Zhu , Eunsol Choi

Recent advances in reasoning models have demonstrated significant improvements in accuracy by employing detailed and comprehensive reasoning processes. However, generating these lengthy reasoning sequences is computationally expensive and…

Computation and Language · Computer Science 2025-08-27 Yijiong Yu
‹ Prev 1 2 3 10 Next ›