LLM策略短板明显，记忆增强代理却能让推理能力飙升，值得关注。
arXiv:2608.12626v1 Announce Type: cross Abstract: Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limite…
推理能力不等于法律边界，论文重新审视欧盟AI法律对推断的规制逻辑，挑战监管假设。
arXiv:2608.10601v2 Announce Type: replace-cross Abstract: Two instruments of EU digital law place inference at their centre and mean different things …
AI 进入医学教育引发新争议：医生还没学会看病，就先学会了依赖算法
IT之家 8 月 12 日消息，据外媒 Futurism 今天（12 日）报道，斯坦福大学医学院医学学生兼记者西马尔 · 巴贾杰、约翰斯 · 霍普金斯医学中心创伤外科医生兼外科执行副主任约瑟夫 · 萨克兰认为， 医学生使用 AI 带来的问题已经相当令人担忧 。 巴贾杰和萨克兰在《卫报》发表文章称，医…
大模型并非只能逐步推理，新观点称LLM也能像人类一样“跳跃”思考，值得一读。
Article URL: https://yongzx.github.io/blog/2026/08/08/llm-can-jump Comments URL: https://news.ycombinator.com/item?id=49232254 Points: 4 # Comments: 0
针对大模型因果推理短板，探究后训练能否带来质的飞跃，实验结论颇具启发。
arXiv:2602.06337v2 Announce Type: replace-cross Abstract: Causal inference is essential for decision-making but remains challenging for non-experts. W…
探索链式递归语言模型如何突破单次推理限制，实现多迭代深度思考，为复杂推理任务提供新范式。
arXiv:2608.05124v1 Announce Type: cross Abstract: Long context reasoning in large language models (LLMs) is usually constrained by the fact that a sin…
大模型类比能力多样性研究揭示AI推理新维度，或为认知智能评估提供全新视角。
arXiv:2608.03233v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable potential for analogy making, a core cogniti…
通过验证器规模化合成长期思维链，大幅提升LLM在数学和编程等场景的推理能力。
arXiv:2509.03059v2 Announce Type: replace Abstract: Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can b…
提出PRO-LONG方法，用程序化记忆突破大模型长程推理瓶颈，论文提出全新思路。
arXiv:2607.20064v2 Announce Type: replace Abstract: Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent …
作者跳出简单LLM界面，动手探索AI Agent如何理解上下文、推理任务并赋能智能工作流
I’m excited to share one of my recent projects — an AI agent application I built to explore how intelligent systems can move beyond simple chat intera…
AI编程助手Claude Code，支持Effort调节平衡推理深度与响应速度，高效解决代码任务。
换更大的模型就等于更聪明？ 【导读】 换更大的模型就等于更聪明？这可能是Claude Code用户最深的误会。很多人为此一路换到最贵的Fable，近日，Anthropic，亲手澄清了这个误区。 你有没有过这种时刻：Claude Code写代码写砸了，第一反应，就是赶紧换个更强的模型。 但这一招，很多…
提出Thinking Seeds方法，利用历史多样性与位置感知强化学习，显著提升LLM推理效率与泛化能力。
arXiv:2601.21476v2 Announce Type: replace Abstract: On-policy reinforcement learning (RL) for language model post-training suffers from a fundamental …
开源论文提出用中间形式规范训练代码大模型，显著提升复杂推理能力。
arXiv:2607.04232v1 Announce Type: cross Abstract: Unlike natural-language specifications, executable formal specifications provide machine-checkable c…
新基准NarrativeTrack专测叙事理解中的实体推理，直击大模型在长文本因果与角色关系上的短板。
arXiv:2601.01095v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved impressive progress in vision-languag…
新基准IsoSci通过同构跨领域科学问题，精准区分大模型的推理能力与知识检索水平。
arXiv:2607.01431v1 Announce Type: cross Abstract: We introduce ISOSCI, a benchmark of isomorphic cross-domain science problem pairs that separates rea…
城市道路复杂场景下，多模态大模型的空间推理真相由RoadBench揭示，自动驾驶进阶必看。
arXiv:2511.18011v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatia…
首个专为医学图像理解设计的思维链基准测试，揭示多模态大模型推理缺陷！
arXiv:2601.08758v4 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by …
大模型能否在可学习性边缘自我进化？ICML 2026新研究揭示自教学推理的极限。
arXiv:2601.18778v3 Announce Type: replace Abstract: RL methods for scaling large reasoning models stall on datasets with low initial success rates, an…
多模态思维链推理究竟强在哪、弱在哪？这项研究用实验拆解其能力边界与局限。
arXiv:2606.22565v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large la…
课程强化学习能否突破基础模型推理上限？这项研究给出新答案。
arXiv:2606.22317v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is widely viewed as a promising path toward co…