1
福田汽车 2030 年锚定百万销量目标，新能源占比 50%
IT之家 9 月 30 日消息，福田汽车 9 月 29 日发布“十五五”战略发展规划， 明确 2030 年整车 100 万辆销量的核心战略目标 。 国际化方面，福田汽车 2026 年 1 至 8 月海外销量近 15 万辆，同比增长 44.3%；截至目前，企业海外累计总销量突破 139 万辆，产品服务…
2
Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learning
揭秘多模态大模型在持续学习中的公平性后门攻击，锚定偏差如何悄然埋下隐患。
arXiv:2608.21577v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in high-stakes domains where fair…
3
Show HN: CookWing, an AI chef that doesn't hallucinate quantities
AI厨师不瞎编调料量？CookWing用溯源锚定表格解决份量幻觉，还自建基准测试。
Hey HN! I just released Cookwing. This is an AI app that solves the biggest problem I had when I was cooking with ChatGPT : The quantities are often h…
4
Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation
大模型微调后“知道却说不出口”的难题，用召回锚定蒸馏可精准破解。
arXiv:2608.20794v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) can degrade factual behavior outside the target domain. This degradation …
5
Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol
面对LLM代理频繁修订判断标准，这项研究揭示失败模式并提出追踪锚定协议，值得AI研究者细读。
arXiv:2608.20729v1 Announce Type: new Abstract: Language-model agents can improve after failure or carry text across episodes without revising what co…
6
Show HN: Inplan – Before Start Coding
把评论锚定在设计文档上，支持图片和多文档，让复杂项目设计更聚焦
Hi HN! I'm one of the makers of inplan, which is a tool to anchor comments to design docs to allow deep/focused design specification. We've improved t…
7
An anchoring layer between facts and AI memory
把AI记忆锚定在可重算的事实上，让主观判断有据可依，轻量开源新思路。
Article URL: https://github.com/Anchorstate-Lab/GMR Comments URL: https://news.ycombinator.com/item?id=49292758 Points: 1 # Comments: 1
8
STAIL: Semantic Text-Anchored Incremental Learning for Medical Imaging via Large Language Models
将大模型语义锚点融入医疗影像增量学习，破解旧知识遗忘难题，值得关注
arXiv:2608.05808v1 Announce Type: new Abstract: Deep learning models applied to medical image analysis suffer from severe catastrophic forgetting when…
9
SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA
用模拟器增强检索，让大模型在长科学问答中更精准地锚定事实，RAG落地新思路。
arXiv:2509.25459v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) show promise in generating long-form scientific explanations th…
10
Constraint-Anchored Reasoning Traces
15页论文提出约束锚定推理痕迹方法，为AI推理提供新视角，ACM MM 2026收录。
arXiv:2607.16727v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorr…
11
Your LLM-as-judge disagrees with itself between runs
LLM作为评判者自身结果不一致？揭秘模型版本漂移与提示模糊性的根源与解法
Same outputs, same judge, two runs, two scores. The gate flickered red then green on a branch with zero code changes, and that flapping cost me more t…
12
Anchored Self-Play for Code Repair
自博弈训练让AI修复代码能力再进一步，锚定策略稳定训练过程，ICML论文值得读。
arXiv:2607.03523v1 Announce Type: cross Abstract: Code repair is an important capability for language models (LMs): given a buggy program and unit tes…
13
To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation
大模型推理常走捷径编造答案，这项研究用提示锚定成对聚合，让推理回归真实逻辑。
arXiv:2606.29481v1 Announce Type: new Abstract: While reinforcement learning (RL) significantly enhances LLM reasoning, its efficacy is severely under…
14
Faithful by Construction: Claim-Anchored Attribution for Multi-Document Summarization
多文档摘要如何做到忠实可溯源？新方法让每条摘要声明都锚定原文依据，从构造上杜绝幻觉。
arXiv:2606.23989v1 Announce Type: cross Abstract: End-to-end large language models (LLMs) produce fluent multi-document summaries but remain prone to …
15
Hidden Anchors in Multi-Agent LLM Deliberation
多智能体LLM讨论中隐藏锚点导致偏差，揭示模型共识机制的关键漏洞。
arXiv:2606.19494v1 Announce Type: new Abstract: Multi-agent LLM deliberation, where agents exchange and revise answers over several rounds, is increas…
16
Localizing Anchoring Pathways in Language Models
探寻语言模型内部语义锚定机制，精准定位关键路径，推动模型可解释性研究。
arXiv:2606.12818v1 Announce Type: cross Abstract: Irrelevant numbers in a prompt can shift language model judgments, producing anchoring effects in nu…
17
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
注意力机制为LLM推理提供“预规划-锚定”节奏，突破强化学习的粗放信用分配，实现细粒度策略优化。
arXiv:2510.13554v2 Announce Type: replace-cross Abstract: The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement lear…
18
eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion
一种新记忆进化机制eMoT，通过符号锚定与记忆腐蚀，在数学推理任务中实现17.6%准确率提升，Game of 24达100%。
arXiv:2606.02054v1 Announce Type: new Abstract: While Large Language Models (LLMs) achieve impressive performance on multi-step reasoning tasks, their…
19
Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time
新方法破解LLM事实幻觉：推理时解耦注意力路由与信号增益，实现上下文共振锚定
arXiv:2606.01923v1 Announce Type: cross Abstract: Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidenc…
20
SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits
提出基于锚定token级logits的LLM越狱检测方法SelfGrader，高效识别对抗性攻击。
arXiv:2604.01473v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain …