大模型能力提升路线图：从"堆参数"到训练全栈 + 外层程序
把 2026 年可核查的公开证据整理成一张六层能力路线图——预训练、后训练 RL、推理时计算、上下文与记忆、智能体与 Harness、世界模型。含 Meta ScaleRL 40 万 GPU 小时实验结论、RL 预算占比 10%–30% 口径、Chinchilla 对比、Meta-Harness 6x 差距等数据锚点，并给出优先级表与算法工程师/产品经理的行动建议。
阅读全文 →
最新文章
LATEST 共 222 条Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems
Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through …
ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
Streaming video understanding is a critical capability for real-world applications, including embodied intelligence, aut…
Unifying Conformal Language Tasks with In-Context Ensembles
Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relevant content from docu…
VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement
Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of …
Causal Foundation Models
Causal inference is the practice of estimating the effect of a treatment or intervention from data. It traditionally req…
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
On-policy distillation (OPD) accelerates post-training by providing dense token-level supervision from a frozen teacher …
MasterControl Seventeen Every Time
We study a governed approach to enterprise analytics: a language model interprets the question, while deterministic poli…
SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models
Long-horizon manipulation is partially observable: the information needed to choose the next action may appear only in o…
EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents
Vision-language-action (VLA) models map visual observations and language instructions directly to robot actions, but lon…
Enoki: Efficient Multi-Level Hallucination Detection
Ensuring factuality remains a critical challenge for deploying LLMs in high-stakes settings. Existing hallucination dete…
Pi 突破 86k Star：组件化 Agent 生态成型
截至 2026 年 9 月，Pi 智能体框架 GitHub Star 突破 86k，pi-ai / pi-agent-core / pi-tui 组件被大量第三方 Agent 项目复用，'自建 Agent 而非套框架'成为新潮流。
Using Grounded Theory for Agent Behavior Analysis at Scale
Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in long, …