LLM 领域动态库
SwarmLabs 专业领域垂直 · 持续迭代中 · 累计实体 156 条（arXiv 133 / 开源仓库 23）。
近期 arXiv 论文（Top 12）
- Multi-Agent AI System for Radiology Report Structuring and Quality Assurance with Independent Radiologist Evaluation
2026-08-18 · Iryna Hartsock, Cesar Lam, Christopher Otteni 等 · 标注: agent - Chain-of-Experience for Continual LLM Improvement
2026-08-18 · Haoqin Tu, Yunhao Fang, Yizhong Wang 等 · 标注: GPT - Against Political Polarization: A Unified Framework for Tracing Evolving Political Ideologies on Social Media
2026-08-18 · Yijie Xu, Chao Wang, Hui Xiong · 标注: — - Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds
2026-08-18 · Md. Faiyaz Abdullah Sayeedi · 标注: reasoning · long-context · RAG - Efficient RLVR Scheduling via Graph-Structured Online Difficulty Estimation
2026-08-18 · Zhizhao Liu, Zhiliang Tian, Xi Wang 等 · 标注: reasoning - BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models
2026-08-18 · Liubov Chubarova, Alexandra Kuleshova, Daniil Volkov 等 · 标注: reasoning · benchmark · multimodal - Encoded but Not Actionable: Auditing the Decode-Generate-Steer Gap in Frozen LLMs for Geometric Constraints
2026-08-18 · Man Liang, Xinzhao Cheng, Faizan Wajid · 标注: reasoning - Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses
2026-08-18 · Alona Strugatski, Licol Zeinfeld, Jason Cooper 等 · 标注: reasoning - Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents
2026-08-18 · Christophe D. Hounwanou, John Emeka Eze, Yaé U. Gaba · 标注: — - SIGMA: SHAP-Guided Implicit-Trajectory Generation for Metadata-Free LLM-Based AutoFE
2026-08-18 · Xuan Zheng, Kento Uchida, Shinichi Shirakawa · 标注: long-context - Procedural Content Metageneration via Program Search and Continual Abstraction Discovery
2026-08-18 · Matthew Siper, Ahmed Khalifa, Julian Togelius · 标注: — - Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs
2026-08-18 · Roman Maksimov, Vladimir Aletov, Vladimir Solodkin 等 · 标注: —
高星开源仓库（Top 12）
- codecrafters-io/build-your-own-x ⭐538127 (Markdown)
Master programming by recreating your favorite technologies from scratch. · 标注: — - public-apis/public-apis ⭐455226 (Python)
A collective list of free APIs · 标注: — - vinta/awesome-python ⭐313098 (Python)
An opinionated list of Python frameworks, libraries, tools, and resources · 标注: — - awesome-selfhosted/awesome-selfhosted ⭐311642 (None)
A list of Free Software network services and web applications which can be hosted on your own servers · 标注: — - torvalds/linux ⭐242283 (C)
Linux kernel source tree · 标注: — - affaan-m/ECC ⭐239028 (JavaScript)
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor · 标注: agent - NousResearch/hermes-agent ⭐227946 (Python)
The agent that grows with you · 标注: agent - multica-ai/andrej-karpathy-skills ⭐200921 (None)
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. · 标注: — - Significant-Gravitas/AutoGPT ⭐186463 (Python)
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters. · 标注: — - ollama/ollama ⭐178141 (Go)
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. · 标注: — - f/prompts.chat ⭐166925 (HTML)
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete pr · 标注: — - firecrawl/firecrawl ⭐164207 (TypeScript)
The context API to search, scrape, and interact with the web at scale. 🔥 · 标注: —
标注为轻量启发式关键词匹配（RLHF/DPO/LoRA/MoE 等），非精确 NER。数据每日累积，详见 data/llm_domain.json。