1
AI 时代的沃尔玛零售员工有了新职责：帮智能体“纠错”
零售员工转行给AI“纠错”，沃尔玛揭示智能体落地的新难题：人工兜底谁来买单？
IT之家 8 月 18 日消息，据《商业内幕》今天（18 日）报道，对沃尔玛零售员工来说，替别人收拾残局原本就是工作的一部分：货架积灰了要擦，液体洒了要清理，展示柜留下污迹也得处理。最近，需要他们帮忙纠正的，又多了 AI 智能体犯下的错误 。 为了推动业务增长，沃尔玛正大举投入 AI，并向数千名前线…
2
Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols
多轮LLM调用中错误如何被纠正或放大？这篇论文提出双速率视角，揭示协议中错误的流动机制。
arXiv:2604.18245v3 Announce Type: replace Abstract: Large language models operate in protocols containing multiple calls, yet added calls are usually …
3
Trace, Verify, and Correct: A Training-Free Framework for Spatial Reasoning in Multimodal LLMs
无需训练，三步纠错，多模态大模型空间推理能力再进一步
arXiv:2608.04759v1 Announce Type: new Abstract: Although Multimodal Large Language Models (MLLMs) have made substantial progress, their spatial reason…
4
全球首个Agentic扩散模型来了：边行动边纠错，128K上下文追平自回归
扩散模型首次打通长程Agent任务
5
Show HN: Quantum hardware now fault-tolerant without extra engineering
无需额外工程实现量子硬件容错，开源项目CIQS通过IBM完整测试，免费可用。
Before you say it's impossible, please go try. --- CIQA, an analytic Quantum Error Correction code, is now freely accessible on GitHub alongside CIQS,…
6
东风日产 NX8 增程 260 Pro 上市，限时换新价 15.99 万元起
您提供的是汽车新闻，不是在线工具。请贴出具体的在线工具链接或名称，我再为您撰写推荐。
IT之家 7 月 10 日消息，东风日产今日宣布，东风日产 NX8 增程 260 Pro 上市，新车官方指导价 16.99 万元， 限时换新价 15.99 万元 。 东风日产 NX8 定位中大型 SUV，长宽高分别为 4870*1920*1680mm，轴距 2917mm。 东风日产 NX8 有增程和…
7
Show HN: Finding better quantum error correction codes using ILP
用整数规划为量子纠错码寻找更优结构，突破经典种子距离上限，性能指标显著提升。
Article URL: https://github.com/ynnk-research/Modular-Assembly-of-High-Performance-Logical-Blocks Comments URL: https://news.ycombinator.com/item?id=4…
8
Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap
RVL-CDIP数据集被曝存在标注错误与测试训练重叠，这项研究量化风险并修订基准，让文档分类评测更可靠。
arXiv:2606.31446v1 Announce Type: new Abstract: RVL-CDIP is a popular dataset for benchmarking document classifiers. However, the dataset contains amp…
9
Quantum computing startup says it will leapfrog everybody
量子计算新锐放弃NISQ路线，宣称2029年实现千级纠错量子比特，剑指行业领先
But the system would require a massive leap from any of its existing hardware.
10
Show HN: Lorentzian CSS Duality in Causal Diamond Quantum Error-Correcting Codes
量子纠错码新突破，CSS对偶与因果菱形结合，12比特码型纠正多类错误，进阶必读。
Article URL: https://github.com/ynnk-research/A-Lorentzian-CSS-Duality-in-Causal-Diamond-Quantum-Error-Correcting-Codes Comments URL: https://news.yco…
11
Evidence for feature-specific error correction in LLMs
揭秘大模型如何在超维叠加中完成纠错，读懂LLM计算的隐藏机制。
arXiv:2606.24964v1 Announce Type: new Abstract: Understanding the features of large language models (LLMs) is a central goal of interpretability. LLMs…
12
Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts
强化学习推理新思路：不直接给答案，引导模型在rollout中自省纠错，提升推理深度。
arXiv:2510.09388v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) …
13
How Far Can Prompting Go for Minimal-Edit Ukrainian Grammatical Error Correction?
探索提示工程在低资源语言乌克兰语上的语法纠错极限，揭示大模型与提示策略的边界。
arXiv:2606.09334v1 Announce Type: new Abstract: Fine-tuned Large Language Models (LLMs) dominate in Ukrainian grammatical error correction (GEC), whil…
14
Evaluating Agentic Configuration Repair for Computer Networks
首个系统性评估AI代理自动修复计算机网络配置错误的能力，揭示代理性能与关键影响因素
arXiv:2606.06212v1 Announce Type: new Abstract: Misconfigurations in computer networks remain a major source of critical Internet outages. Research is…
15
Structure Enables Effective Self-Localization of Errors in LLMs
利用结构信息让大模型精准定位自身推理错误，提升可靠性与可解释性。
arXiv:2602.02416v2 Announce Type: replace Abstract: Self-correction in language models remains elusive. In this work, we explore whether language mode…
16
Evolutionary Discovery of Bivariate Bicycle Codes with LLM-Guided Search
LLM引导进化搜索，发现双变量循环码，革新量子纠错码发现效率
arXiv:2606.02418v1 Announce Type: cross Abstract: Quantum LDPC code discovery requires searching large algebraic design spaces while reliably certifyi…
17
CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
ACL 2026 录用：用思维链推理 + 强化学习让中文文本纠错更高效准确
arXiv:2606.00020v1 Announce Type: cross Abstract: Large Language Model (LLM) based Chinese Grammatical Error Correction (CGEC) systems face two critic…
18
SERC: LDPC-Inspired Semantic Error Correction for Retrieval-Augmented Generation
受LDPC纠错码启发，提出语义纠错方法SERC，显著提升RAG的检索与生成一致性。
arXiv:2605.28837v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have demonstrated remarkable capabilities, their reliability is s…