#Reasoning

智能AI None

MAMath-Bench：多模态多智能体数学推理的过程感知和鲁棒评估

arXiv:2610.26943v1 Announce Type: new Abstract: Mathematical reasoning is a fundamental capability for educational appli

reasoning and the

2026-10-21 Xinping Wang, Jie Ma, Rui Xing, Wensong Guo, Xiayi Zhang, Jianhao Deng, Zihao Zhou, Boqian Yang, Feijuan He

智能AI None

Agent推理快10倍是怎么做到的？苹果×CMU：把「生成」改成「做选择题」

在智能体的典型工作流程中，模型每执行一个动作之前，都要先生成一段自由形式推理（free-form thinking）：分析当前观察、评估已有证据、再决定下一步行动。这一 “思考” 过程是 ReAct 范式的核心环节，但也带来了实打实的推理开

Reasoning token Agent

2026-10-16 机器之心

智能AI None

TimeThink：在时间序列大型语言模型中引发组合推理

arXiv:2609.13457v1 Announce Type: new Abstract: Timeseries multimodal large language models (TS-MLLMs) have recently beg

reasoning models the

2026-09-15 Sudarshan Regmi, Arvind Pillai, Yu Yvonne Wu, Yuliang Chen, Bibek Panthi, Tess Z. Griffin, Michael V. Heinz, Lisa Marsch, Nicholas C. Jacobson, Andrew Campbell

智能AI None

模块化认知架构出现在大型语言模型中

arXiv:2608.13567v1 Announce Type: new Abstract: The human brain exhibits a striking degree of functional specialization,

reasoning networks the

2026-08-17 Pengrui Han, Jacob Andreas, Evelina Fedorenko, Andrea Gregor de Varda

智能AI None

立场：推理是一个可学习的基于规则的过程

arXiv:2608.12325v1 Announce Type: new Abstract: Autonomous reasoning is among the most scientifically and economically m

reasoning the and

2026-08-15 Rachel Lawrence, Jacqueline Maasch

开源推荐 None

GitHub 热门项目：Mulberry

GitHub项目：Mulberry 仓库地址：https://github。

https Mulberry com

2026-06-26 GitHub Trending

智能AI None

神经符号驱动：驱动 VLA 的基于规则的忠实推理

arXiv:2606.23938v1 Announce Type: new Abstract: Driving VLA models incorporating Chain-of-Thought (CoT) reasoning are at

the and reasoning

2026-06-24 Xiangbo Gao, Xiukun Huang, Boyu Lu, Junge Zhang, Mengjie Mao, Jiachen Li, Wei Xiong, Zhengzhong Tu

开发者生态 None

VibeThinker：3B 参数模型在推理上击败 Opus 4.5，采用新颖的 SFT+GRPO

Computer Science > Artificial Intelligence arXiv:2606。

the and reasoning

2026-06-23 timhigins

智能AI None

在LLM推理中，除了价值错位之外还存在非理性

20624v1 Announce Type: new Abstract: Significant progress has been made in aligning LLMs with target value functions。

value and the

2026-06-23 Kejiang Qian, Fengxiang He

智能AI None

使用人工智能帮助医生诊断影响儿童的罕见遗传病

Researchers used an OpenAI reasoning model to help diagnose rare diseases, identifying 18 new diagnoses in previously un

Researchers used OpenAI

2026-06-18 OpenAI博客

智能AI None

通过结构不确定性量化法学硕士逻辑推理的一致性

arXiv:2606.17312v1 Announce Type: new Abstract: Large language models can arrive at the same answer through reasoning pa

reasoning the and

2026-06-17 Baishali Chaudhury, Mengdie Flora Wang, Hyunji Hayley Park, Rahul Ghosh, Sungmin Hong, Jae Oh Woo

智能AI None

PrologMCP：LLM 代理的标准化 Prolog 工具接口

arXiv:2606.14935v1 Announce Type: new Abstract: Frontier reasoning-tuned language models still fail on deductive tasks a

the reasoning and

2026-06-16 Agnieszka Mensfelt, Adarsh Prabhakaran, Adrian Haret, Vince Trencsenyi, Kostas Stathis

智能AI None

将预测未来行为作为一项学习任务

11445v1 Announce Type: new Abstract: Trust in an AI system is often anchored by explanations of how it works, which one

the and that

2026-06-11 Mosh Levy, Yoav Goldberg, Asa Cooper Stickland

智能AI None

为什么将剩余流限制为层而不是令牌？用于连续潜在推理的持久记忆

07720v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable reasoning abilities on ma

reasoning the and

2026-06-09 Mujtaba Farhan, Maheep Chaudhary

智能AI None

CrowdMath：众包数学研究讨论的数据集

arXiv:2606.06526v1 Announce Type: new Abstract: Large language models have made substantial progress on mathematical rea

the progress mathematical

2026-06-08 Sherin Muckatira, Jesse Geneson, Slava Gerovitch, Pavel Etingof, Mikhail Gronas, Anna Rumshisky

智能AI None

多少思考才足够？量化和理解法学硕士推理中的冗余

23926v1 Announce Type: new Abstract: Reasoning-capable large language models solve hard problems by emitting long chains

the and models

2026-05-26 Zhiyuan Zhai, Xinkai You, Wenjing Yan, Xin Wang

智能AI None

LLM 何时进行推理？通过熵相变的动态系统视图

arXiv:2605.22873v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enh

and entropy reasoning

2026-05-25 Wei Xia, Haoqing Wang, Zhi-Hong Deng, Yehui Tang

智能AI None

MindLoom：构建前沿级推理数据合成的思维模式

21630v1 Announce Type: new Abstract: Although LLMs have made substantial progress in reasoning, systematically producing

reasoning and MindLoom

2026-05-23 Haiyang Shen, Taian Guo, Xuanzhong Chen, Mugeng Liu, Weichen Bi, Wenchun Jing, Sixiong Xie, Zhuofan Shi, Yudong Han, Chongyang Pan, Siqi Zhong, Jinsheng Huang, Ming Zhang, Yun Ma

智能AI None

OSCToM：强化学习引导的高阶心理理论对抗生成

20423v1 Announce Type: new Abstract: Large Language Models (LLMs) perform well on many language tasks, but their Theory

the and OSCToM

2026-05-22 Sharmin Sultana Srishty, Kazi Mahathir Rahman, Malaika Parizat Sakkhi, Samia Shahid Prianna, Shaikhul Islam Sinat

智能AI None

OpenAI 声称它解决了一个 80 年前的数学问题——这次是真的

OpenAI claims its reasoning model disproved a geometry conjecture unsolved since 1946 — and this time, the mathematician

its OpenAI claims

2026-05-20 Rebecca Bellan