2026年11月1日 技术热点总结

项目简介：Towards a More Autonomous Agent System

技术栈：TypeScript

核心介绍：> Research prototype for reference only, not an official DeepSeek product. This code grew out of our team’s day-to-day development work, with much of the engineering done by coding agents. Treat it as research code, not production-ready software. It may still contain bugs, and its coding style and engineering practices may be inconsistent. Review and adapt it before using it in your own environment.

项目数据：⭐ 2,234 Stars，🍴 192 Forks

项目简介：1407 张 AI 女装参考图集与虚拟试穿网站，支持中英检索、OpenAI Images / Gemini / 豆包及自定义 Base URL、API Key、模型。https://github.com/paipiange/nvzhuang

技术栈：Go

核心介绍：一个深色主题的纯净服装参考图集网站，收录 1407 张 人物不入镜的 AI 生成服装图像（2:3 比例），支持中英文双语浏览、多维检索，并配备可选的 AI 一键换装试穿。 > 👗 【Linux.do 3级常任理事专属彩蛋】 > 听说在 LINUX DO 社区只要升到 3 级（常任理事） 就可以解锁“看女装大佬”的保留节目？身为一名尊贵的 Linux.do 3 级老兵，逛了一圈发现坛里的女装资源还不够看，干脆亲手搓了这个 「拍片哥女装」 项目！ > 不仅收录了 1407 套纯净高质量服装图，还顺手接了 AI 虚拟换装后端——这下各位佬友哪怕现实中没有小裙子，直接传张自拍照就能一键无痛变身“女装大佬”出道了 😂！ > 🔗 在线预览：https://paipiange.github.io/nvzhuang/ > ⭐ GitHub 源码：https://github.com/paipiange/nvzhuang

项目数据：⭐ 1…

项目简介：Git for Global Law: the law of every country as one git history, each country’s record a submodule, every commit one law taking effect

技术栈：HTML

核心介绍：An expansion of the same for the US Code, #1 on Hacker News (28/10/26). Semantic, searchable law on a global scale. sits in each country’s repository, under that repository’s own terms. The law of many jurisdictions as one git history. Each jurisdiction’s law is its own repository, where every commit is one law taking effect, written by that law. This repository arranges those repositories by jurisdiction and

项目数据：⭐ 1,39…

Quarterly earnings forecasting requires an agent to connect financial evidence to the income-statement line items that produce a company's reported earnings. We introduce EPSBench, a benchmark for studying this ability across 149 firm-quarters from 86 US companies. Agents read a fixed collection of filings, earnings-call transcripts, and news, then estimate company-specific income-statement drivers with cited evidence. A shared accounting calculator converts these estimates into GAAP diluted earnings per share (EPS), providing a common basis for comparing forecast assumptions. We evaluate s…

Self-distillation offers a way to improve reasoning models when a suitable external teacher is unavailable. However, common approaches rely on privileged information to construct a stronger self-teacher, limiting their use when only unlabeled prompts are available. In this paper, we introduce Weakening-Induced On-Policy Self-Distillation (WISD), which instead constructs a weaker counterpart of the original model and uses the contrast between the two as a training signal without requiring privileged information. We explore two ways to construct the weaker model: low-bit quantization and magn…

Autoregressive (AR) image generators are powerful in principle but inflexible in practice: training with a fixed raster-scan order hardcodes a single factorization of the image distribution into the model, leaving it unable to inpaint, outpaint, or edit at inference time. Existing solutions, including the modern discrete-diffusion family, train from scratch on a mixture of token orderings, paying roughly 3x the compute of standard raster-scan training; discrete diffusion further sacrifices compatibility with the AR inference ecosystem (KV caching, vLLM) by construction. We argue that this c…

Language agents increasingly act through external tools and interactive environments, making the interface between the model and its executable capabilities part of the decision process. Model Context Protocol (MCP) and command-line interfaces (CLI) can expose the same semantic operations through markedly different model-facing representations. We study whether these representational differences change agent behavior when executable capabilities are matched. We introduce Matched Interface Comparison and Analysis (MICA), which renders MCP and CLI from a shared semantic action contract and ro…

Developers download quantized large language models (LLMs) from public registries to run them locally. None of the registries we examined documented functional testing of their files. We tested all 305 eligible code-capable GGUF tags (the llama.cpp format) across 15 model lines in the official Ollama library, plus 22 popular Hugging Face community files. A 15-task code screen identified suspects, which we retested on all 164 HumanEval+ tasks. Seven official tags (2.3%) solved at most six of them. All were low-bit quantizations of models with at most four billion parameters. We rebuilt five …

Foundation models are typically trained in stages: pretraining, midtraining, supervised fine-tuning (SFT), and reinforcement learning (RL), with changes in both data and learning algorithms. We show that this algorithmic separation is not fundamental. By deriving suitable RL objectives as maximum-likelihood fitting to model-generated target distributions, we place all of these stages under a single likelihood-based training algorithm, unified training. This perspective turns the foundation-model training lifecycle into a problem of choosing which data to train on, in what proportions, and w…