Full-text search across 70872 articles. Combine with topic and date filters; results sorted by relevance.
Researchers propose ProGAP, a transferable graph purification scheme that uses vulnerability-aware graph prompt learning to bridge adversarial defense knowledge across domains, improving robustness of Graph Neural Networ…
A new arXiv preprint (2608.28911v1) introduces SemKV, a semantic mixed-precision KV cache quantization method that achieves a measured 6.0x storage reduction for long-context LLM inference with no statistically detectabl…
Researchers at IIT Gandhinagar introduced GurukulAI, an AI-driven educational platform tailored to the Indian education system, built on a new syllabus-aligned dataset of 18,720 question-answer pairs from NCERT textbooks…
Researchers propose ERR+, a two-phase reinforcement learning framework that improves large reasoning models' accuracy and response conciseness by rewarding token-level entropy drops in chain-of-thought traces. In experim…
A new open-source toolkit aims to standardize text-to-speech (TTS) model testing by providing a structured framework for automated evaluation, addressing the lack of unified benchmarks in the field. The toolkit focuses o…
Mu/TH/UR 6000, an anonymous AI terminal styled as a 1979 mainframe, has launched, offering uncensored, agentic AI capabilities including code writing, research, planning, and persistent memory. The terminal, which requir…
Sony Music Publishing and Warner Chappell's copyright case against Anthropic alleges copyrighted songs were scraped to train Claude, with damages that could reach billions, while researchers identified 120 unclaimed pack…
Etherscan released a suite of tools on August 31, 2026, enabling AI agents and coding assistants to pull live blockchain data from its API across more than 60 EVM-compatible chains. The 'Build with AI' launch includes a …
OpenAI will end its partnership with Cursor, the AI-coding agent, after SpaceX's acquisition of the company, with a proposed shutoff date of Nov. 12. OpenAI stated it cannot be confident that SpaceX will use its technolo…
Io.github.HarimxChoi/google-surf-mcp version 1.0.2, a web, academic and code search tool with graph RAG, data lineage, ontology and cross-project schema links, was published to the official MCP registry on 2026-08-31 and…
Frontier AI models are identifying vulnerabilities in open source software faster than human researchers, but remediation is not keeping pace, creating a widening gap that now affects 82% of organizations, up from 74% th…
Mark Murphy reports that mlx-serve, an Ollama-like inference server with a GUI, delivers a 4x speed increase for running Qwen 3.8 on his 64GB M2 Ultra Mac Studio compared to his previous Ollama setup, thanks to better ML…
The latest release of spfx-factory, an open-source tool for generating SharePoint Framework (SPFx) projects, introduces an evidence-gated workflow that records verification results for each step of the generation process…
Pagecord, a blogging platform, has published a dedicated /ai page at https://pagecord.com/ai to disclose all its AI usage, following the '/ai manifesto' convention by Damola Morenikeji and tracked at slashAI.page. The pa…
A developer demonstrates building a Retrieval-Augmented Generation (RAG) application using Spring AI, connecting large language models to private data sources. The post outlines the RAG pipeline, including document loadi…
A Hacker News user is asking for examples of companies discussing their AI/agentic workflows, citing Wes McKinney's blog post on agentic engineering at Kenn as a reference. The user seeks similar deep dives into professi…
OpenBot, an open-source project, has gained 3,593 stars on GitHub within 15 days of its release, according to the Agentic Leaderboard's weekly report for the week of 2026-08-31, which evaluated 100 agents. The leaderboar…
A multi-agent system of large language models autonomously solved five major open problems in mathematics, including new finite-field Kakeya sets and improved bounds on Erdős's minimum-overlap problem, according to a pap…
A developer argues that AI agents often fail not due to poor prompts but due to a lack of real tools, and demonstrates how equipping an agent with simple functions like running tests can dramatically improve performance.…
Jie Wang of Southwest University of Political Science and Law is seeking endorsement from arXiv cs.LG moderators for a paper titled 'Coupled Scaling: A Representational Accessibility Framework for Neural Scaling Laws,' w…