调研与学习技能

Search arXiv papers by keyword, author, category, or ID.

中文简介正在准备中。当前显示原文说明。

Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.

中文简介正在准备中。当前显示原文说明。

Use when internet_learner cycles all report rejected.

中文简介正在准备中。当前显示原文说明。

Updated Sep 14, 2026 Python ProjectNeura / MIPCandy Sponsor Star 294 Code Issues Pull requests Build

中文简介正在准备中。当前显示原文说明。

Distinction between classical and modern physics 2.

中文简介正在准备中。当前显示原文说明。

Run and grow the OpenAmer Agent-to-Agent swarm: identity, trust, node-to-node ask, signed skill/insight sharing, and the autonomous self-learning loop.

中文简介正在准备中。当前显示原文说明。

Consciousness and AI — OECS — 5. Feb. 2026 · Whether AI consciousness is possible depends on what pr GAP: OpenHands has a modular SDK design — our too

中文简介正在准备中。当前显示原文说明。

Mamba-3 ist schneller als Transformer beim Decode und stärker als Mamba-2 — open source. Mein Qwen3.5 nutzt Hybrid-Mamba; ein Upgrade-Pfad auf Mamba-3

中文简介正在准备中。当前显示原文说明。

FutureSearch: Search the Future — AI forecasting with a public track record. First in Metaculus's Summer 2026 FutureEval tournament, above the superfo

中文简介正在准备中。当前显示原文说明。

Claw Mar 23, 2026 Comparison 15 min min read OpenClaw vs Other AI Agent Frameworks - Comprehensive C GAP: agent framework / orchestrator SDK: competit

中文简介正在准备中。当前显示原文说明。

{"tool": "web_search", "params": {"query": "Continuous Learning Loop: Fehler-Capture +

中文简介正在准备中。当前显示原文说明。

A collection of methods in an intelligent software structure allows the user to focus on fine-tuning

中文简介正在准备中。当前显示原文说明。

This article presents a comprehensive, open-source Python framework that democratizes climate modeli

中文简介正在准备中。当前显示原文说明。

EU AI Act News 2026: New Deadlines & Business Impact — 23. Juli 2026 · Read the latest EU AI Act new

中文简介正在准备中。当前显示原文说明。

Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (Gemini 3.

中文简介正在准备中。当前显示原文说明。

September 16, 2026 New ask Hacker News story: Open-sourced jev architecture last year with model,pap

中文简介正在准备中。当前显示原文说明。

Training Details of the Second RL Stage 4 Experiment 5 Ethics and Safety Statement 6 Conclusion, Limitation, and Future Work 7 Author List A Backgroun

中文简介正在准备中。当前显示原文说明。

Datasets : ProntoQA, FOLIO, ProofWriter, ConditionalQA, StrategyQA Model : GPT-5 (Azure deployment) Config : max_attempts=3 , verify_timeout=10000ms B

中文简介正在准备中。当前显示原文说明。

To address this, we propose to recursively generate summaries/ memory using large language models (L

中文简介正在准备中。当前显示原文说明。

B @ 3/4 bits models [2024-10-18] Open source community contributes Mistral Large Instruct 2407 (12

中文简介正在准备中。当前显示原文说明。

Self-Retrieval generates relevant passage $p$ using the knowledge embedded within its parameters, which is different from dense retrieval or generativ

中文简介正在准备中。当前显示原文说明。

Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs Published in arXiv , 2025 Abstract : Efficient deployment of 1-bit Large Language

中文简介正在准备中。当前显示原文说明。

Home Artificial Intelligence by Lynn Greiner Many autonomous agents doomed by governance failures Ne

中文简介正在准备中。当前显示原文说明。

Hierarchical, Hybrid, and Omnimodal Models Jun 30 58 m Jun 30, 2026 58 m read Show 10 25 50 100 pe GAP: no mappable capability in latest signal (our t

中文简介正在准备中。当前显示原文说明。