搜索:llms.txt

共命中 50 条(服务端检索)
智能体生态观察 · 第 81 篇|开发者文档的 Agent 化:llms.txt、机器可读与文档新形态
开发者文档的第一读者正在变成非人类。本篇从文档工程视角拆解 Agent 可读实践:llms.txt 导览与 Markdown 直链、语义锚点与可执行示例、双形态渲染的收益与维护成本,并观察 llms.txt 的标准采纳、文档工具链的 Agent 化改造与文档工程师的角色迁移。
智能体 精选 · 原创 · 今天 阅读 1·访客 1
OpenAI、Google、Microsoft、Anthropic 共同支持 robots.txt 统一 AI 训练退出令牌 __usage_ai-training
OpenAI、Google、Microsoft 与 Anthropic 宣布共同支持 robots.txt 中的 __usage_ai-training 令牌,网站一条声明即可统一拒绝 AI 训练抓取,Google 与 Microsoft 计划 2027 年落地。
行业动态 The Verge · 11-1 阅读 30·访客 30
The Narrative Gap: Can LLMs Help Us Navigate Diverse Narratives Across Languages?
Large language models (LLMs) increasingly mediate how people seek and consume information, including accounts that diffe…
大模型 HuggingFace Daily Papers · 11-9 阅读 4·访客 4
Coding or Cheating? An Investigation of Frontier Coding LLMs
Frontier agentic LLMs are trained on verifiable rewards in reinforcement learning (RL) environments built from real soft…
智能体 HuggingFace Daily Papers · 11-7 阅读 7·访客 7
Sherpa: Teaching LLMs to Teach Adaptively
Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is not …
大模型 HuggingFace Daily Papers · 10-6 阅读 26·访客 26
Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation
Large language models (LLMs) are increasingly used as interactive agents and simulators, yet it remains unclear whether …
智能体 HuggingFace Daily Papers · 10-4 阅读 70·访客 69
Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs
Generalization in large language models (LLMs) is the ability to produce consistent and semantically stable outputs when…
大模型 HuggingFace Daily Papers · 10-1 阅读 22·访客 22
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation
Backdoor attacks can be implanted in Large Language Models (LLMs) during training, causing unwanted behaviour when a tri…
大模型 HuggingFace Daily Papers · 9-29 阅读 33·访客 33
Multilinguality in Hybrid Attention LLMs
In response to the growing demand for long sequences in agentic and reasoning use cases, many state-of-the-art LLMs comb…
智能体 HuggingFace Daily Papers · 9-28 阅读 74·访客 74
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit f…
大模型 HuggingFace Daily Papers · 9-24 阅读 33·访客 33
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregressive LLMs by enabl…
大模型 HuggingFace Daily Papers · 9-22 阅读 30·访客 30
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up
We demonstrate that training LLMs with RL does not improve performance equally across a dataset. RL shows large improvem…
大模型 HuggingFace Daily Papers · 9-11 阅读 37·访客 37
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) str…
智能体 HuggingFace Daily Papers · 9-3 阅读 64·访客 63
TempCloze: Can Video-LLMs Identify the Missing Middle?
Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from …
研究前沿 HuggingFace Daily Papers · 9-1 阅读 28·访客 27
Google、微软与 OpenAI 计划支持共享的 AI 训练退出标记
Search Engine Journal 报道,Google、Microsoft 与 OpenAI 计划支持共享的 AI 训练退出标记,站点通过一行 robots.txt 即可向多家提供商同时声明拒绝。
行业动态 Search Engine Journal · 11-3 阅读 25·访客 25
智能体生态观察 · 第 68 篇|浏览式理解:从爬虫解析到智能体浏览的范式迁移
喂给智能体的网页数据正在换代:选择器脚本快而脆,真实浏览器浏览慢而稳,成本差一到两个数量级。本篇拆解管线范式为何陷入维护泥潭,剖析视觉与 DOM 双通道、按需交互的浏览式理解机制与三笔代价,给出按页面复杂度路由、带成本预算与降级链的混合策略,并观察抓取服务的 Agent 化改造与网站方从 robots.txt 到按次付费的态度分化。
智能体 精选 · 原创 · 今天 阅读 3·访客 3
Stanford Research Open-Sources Memorilla, a Latent Memory Module for Frozen LLMs
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
开源项目 MarkTechPost · 5天前 阅读 24·访客 24
PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models
Video generation models produce visually realistic videos but still struggle with physical dynamics and causal consisten…
大模型 HuggingFace Daily Papers · 11-12 阅读 3·访客 3
SIRIS: Can LLMs Tell When Simulation Errors Matter in AI-Driven Systems Research
LLM agents increasingly drive systems research and rely on simulators to evaluate candidate designs at scale. Simulators…
智能体 HuggingFace Daily Papers · 11-6 阅读 9·访客 9
Universal Textual Teaching for LLMs
Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods …
大模型 HuggingFace Daily Papers · 10-8 阅读 27·访客 27
Don’t be fooled—LLMs don’t reason
On an afternoon in Seoul in March 2016, I watched a program I helped build put a stone on the fifth line of a Go board i…
大模型 MIT Technology Review · 10-2 阅读 57·访客 54
The Download: a biological de-aging contest and why LLMs don’t reason
This is today's edition of* *The Download*,*our weekday newsletter that provides a daily dose of what's going on in the …
大模型 MIT Technology Review · 10-2 阅读 52·访客 48
When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs
Before invoking external tools, an agentic LLM must select among a K-way action space: executing a call, seeking clarifi…
智能体 HuggingFace Daily Papers · 9-28 阅读 75·访客 74
Towards Full Pipeline FP8 Reinforcement Learning for LLMs
Reinforcement learning (RL) has become a key technique for improving the reasoning and agentic abilities of large langua…
智能体 HuggingFace Daily Papers · 9-19 阅读 84·访客 83
Best Open-Source Agent Harnesses for Local LLMs in 2026
Which open-source harness works with Ollama, LM Studio, or llama.cpp? 11 verified picks with licenses and setup rules. T…
智能体 MarkTechPost · 9-18 阅读 119·访客 115
HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
Scientific agents contribute to hypothesis discovery by synthesizing evidence, assessing proposals, and developing new e…
智能体 HuggingFace Daily Papers · 9-14 阅读 85·访客 84
X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks per…
大模型 HuggingFace Daily Papers · 9-10 阅读 49·访客 46
Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?
Repository-level coding benchmarks have become the standard for evaluating coding agents, yet they inherently suffer fro…
智能体 HuggingFace Daily Papers · 8-21 阅读 85·访客 84
G-CAST: Governed Continual Self-Training for E-Commerce Agents under Evolving Demands
With the rapid advancement of Large Language Models (LLMs), an increasing number of users are turning to LLM-powered age…
智能体 HuggingFace Daily Papers · 6天前 阅读 2·访客 2
More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs
Evaluations of multi-agent language models often compare communicating architectures against a single greedy pass. This …
智能体 HuggingFace Daily Papers · 6天前 阅读 3·访客 3
AI Reviews Are Biased Towards the Appendix
Large language models (LLMs) are increasingly used by reviewers to highlight weaknesses during the reviewing process, an…
大模型 HuggingFace Daily Papers · 6天前 阅读 2·访客 2
JFinBench: A Continuously Refreshable Japanese Financial Benchmark from the Latest Certification Exams
Large language models (LLMs) are increasingly applied to finance, creating a need for benchmarks that evaluate their cap…
研究前沿 HuggingFace Daily Papers · 6天前 阅读 2·访客 2
From Large Language Models to Efficient System One Models via Adaptive Computation
Transferring LLMs into System One decision models typically replaces the language modeling head with a decision head whi…
大模型 HuggingFace Daily Papers · 11-12 阅读 3·访客 3
Experience-Handoff Reinforcement Learning for Recursive Self-Improvement
It is common to train Large Language Models (LLMs) for agentic tasks with Reinforcement Learning (RL) from scalar reward…
智能体 HuggingFace Daily Papers · 11-12 阅读 3·访客 3
FraudBench: A Legal Evaluation of AI Deception
We introduce FraudBench, an evaluation of large language models' (LLMs) propensities to recommend, assist, or directly t…
大模型 HuggingFace Daily Papers · 11-9 阅读 13·访客 13
Subliminal Learning in Vision-Language Models
Subliminal learning is a phenomenon in large language models (LLMs) where a teacher passes a hidden preference to a stud…
大模型 HuggingFace Daily Papers · 11-4 阅读 2·访客 2
IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?
Research taste, the judgment of what to read, which problems to pursue, and which methods to try, increasingly shapes th…
大模型 HuggingFace Daily Papers · 11-2 阅读 23·访客 23
Cross-Primitive Consistency in Jev
Jev enables efficient decision-making with large language models (LLMs) through typed querying primitives, allowing the …
大模型 HuggingFace Daily Papers · 10-28 阅读 9·访客 9
Follow the Gradient: Tracing Safety Degradation Back to Training Data
Fine-tuning Large Language Models (LLMs) on instruction data can quietly erode their safety, even when no training examp…
大模型 HuggingFace Daily Papers · 10-27 阅读 17·访客 17
GEPA-Curator: Curated Learning for Self Improving Agents
Large Language Models (LLMs) are increasingly used in multi-turn agentic workloads that require sustained interaction wi…
智能体 HuggingFace Daily Papers · 10-27 阅读 16·访客 16
Advancing SVD-based LLM Compression via Layer-Wise Error Model Search
Low-rank SVD-based compression offers a powerful strategy to reduce the computational costs of LLMs. However, existing m…
大模型 HuggingFace Daily Papers · 10-23 阅读 20·访客 20
Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding
Decoder hidden states from different layers of large language models (LLMs) often encode complementary information. Howe…
大模型 HuggingFace Daily Papers · 10-9 阅读 40·访客 39
GraphDecisionBench: Benchmarking System One Models on Graph Tasks
Large language models (LLMs) are increasingly explored for graph understanding and decision-making, while System One mod…
研究前沿 HuggingFace Daily Papers · 10-9 阅读 29·访客 29
DataVista: Diagnosing Multimodal LLMs on Data Video Understanding
Data video is a media form that integrates data visualization with video narrative, widely adopted in news reporting and…
大模型 HuggingFace Daily Papers · 10-8 阅读 22·访客 22
Incidental information contaminates patient notes and disrupts clinical reasoning in large language models
Large language models (LLMs) are increasingly relied upon to support ambient documentation and clinical reasoning. Here …
研究前沿 HuggingFace Daily Papers · 10-6 阅读 34·访客 34
Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI
Large language models (LLMs) and vision-language models (VLMs) are usually frozen after deployment, so they do not learn…
大模型 HuggingFace Daily Papers · 10-6 阅读 28·访客 28
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Reinforcement learning (RL) for post-training large language models (LLMs) incurs substantial computation and memory ove…
大模型 HuggingFace Daily Papers · 10-6 阅读 40·访客 40
Towards In-Parameter Memory Augmentation for Large Language Models
Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pre…
智能体 HuggingFace Daily Papers · 10-6 阅读 83·访客 82
Stepped MoE: Segment-Level Routing with Configurable Inference Complexity
Training large language models (LLMs) is resource-intensive, and adapting them for diverse deployment scenarios with var…
大模型 HuggingFace Daily Papers · 10-5 阅读 33·访客 33
Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation
Reasoning traces improve large language models (LLMs), but current models are trained to reason mostly in English. It ha…
研究前沿 HuggingFace Daily Papers · 10-2 阅读 28·访客 28