Search: “agents”

arXiv:2604.11661v1 Announce Type: cross Abstract: Large language models (LLMs) have recently gained significant attention as a promising approach to accelerate scientific discovery. However, their app

arXiv:2604.10480v1 Announce Type: new Abstract: Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs), yet datasets are often treated as isolated artifact

just finished this. genuinely one of the most informative episodes I've heard in a while the future of engineering is changing faster than most people realize. and it's self-managed, self-improving ag

Harrison Chase, co-founder of LangChain, shared or engaged with a post on X (formerly Twitter) praising LangChain's developer relations team for producing high-quality technical and educational conten

arXiv:2604.09511v1 Announce Type: new Abstract: Universal image restoration (UIR) aims to recover clean images from diverse and unknown degradations using a unified model. Existing UIR methods primari

“Above the api line” Good phrase GBrain is my attempt to be in control of my own personal AI that could become my intentionally designed cognitive armor Open source open prompts means you aren’t under

Harrison Chase, co-founder of LangChain, has shared perspectives on X (formerly Twitter) distinguishing 'harness engineering' from traditional prompt engineering, suggesting a conceptual evolution in

if you don't own your harness, you don't own your memory this is so true. even though Codex is an open source, it generates an encrypted compaction summary (that is not usable outside of the OpenAI ec

Only OG's know @NousResearch had bots back in 2024. This is when models were not capable. They've tried to solve this problem every way possible. Even @karan4d was exploring such ideas acitvely, @max_

The differentiating factor between a prototype and an autonomous system is no longer solely the underlying model weights, but the sophistication of the orchestration layer and its capacity for continu

Cloudflare's mission has always been to help build a better Internet. Sometimes that means building for the Internet as it exists. Sometimes it means building for the Internet as it's about to become.

@hwchase17 @sarahwooders like a the old children's school flipbook - each one wakes up, takes in the context(memory) via harness does its thing, then rests.... next flip book page, the harness manages

Nous Research partnered with Xiaomi to integrate Xiaomi's MiMo V2 Pro inference model into its Hermes Agent framework, making it accessible via the Nous Portal for a two-week free trial period. The...

In the enterprise landscape, data is often highly fragmented across multiple source systems. Data curation is the process of organizing, cleaning, and enriching raw data to transform it into high-qual

arXiv:2604.06323v2 Announce Type: cross Abstract: Blockchain and artificial intelligence (AI) are increasingly proposed together for securing intelligent networks, but the literature remains fragmente

In today's data-rich environment, organizations possess vast amounts of information. Yet, bridging the gap between that data and the users who need to make daily, informed decisions remains a challeng

arXiv:2604.02360v1 Announce Type: cross Abstract: The transformative potential of large language models (LLMs) in education, such as improving accessibility and personalized learning, is being eclipse

GLM-5.1, developed by Z.ai (formerly Zhipu AI), is Z.ai's next-generation flagship model for agentic engineering, featuring 'significantly stronger coding capabilities than its predecessor,' bette...

Waldium is a YC-backed, two-person agentic CMS that automates content research and creation, and gives every customer blog its own Model Context Protocol (MCP) server endpoint so AI agents can quer...

arXiv:2604.08203v1 Announce Type: new Abstract: Medical Vision-Language Models (VLMs) hold immense promise for complex clinical tasks, but their reasoning capabilities are often constrained by text-on

arXiv:2509.23322v2 Announce Type: replace Abstract: With the continuous expansion of Large Language Models (LLMs) and advances in reinforcement learning, LLMs have demonstrated exceptional reasoning c

Ramp has launched **AI Spend Intelligence**, a new product that gives finance teams token-level visibility into AI costs across providers like OpenAI and Anthropic. The New York-based company pull...

arXiv:2604.04956v2 Announce Type: replace-cross Abstract: The recent, super-exponential scaling of autonomous Large Language Model (LLM) agents signals a broader, fundamental paradigm shift from machi

Sam Morrow, a Senior Software Engineer at GitHub on the Copilot Agent Services team, spoke at the ai.engineer conference about the challenges of building and scaling the GitHub MCP Server — an open...

Wrapped up the 3-day AI Engineer conference in London. Key takeaways: Planning & verification > implementation. Humans define what to build and validate it works. AI handles the coding. The harness ma

March ships Foundry Agent Service GA with private networking, GPT-5.4 and GPT-5.4 Mini, Priority Processing, Phi-4 Reasoning Vision, SDK 2.0 GA across Python, JS/TS, Java, and .NET, Fireworks AI and

'Claude Code isn't magic. The harness layer is just software, and software is something any dev can shape to fit how they want to work.' Check out @Hacubu’s practical guide to building a custom agent

🤖 【2026最新】1秒で理解！8時間自律稼働する「GLM-5.1」がLinuxをゼロから構築。オープンソースが世界を制す極限全貌 【2026最新】1秒で理解！8時間自律稼働し、Linuxデスクトップをゼロから完成させる衝撃のオープンソースAI「GLM-5.1」が登場。SWE-Bench Proで世界3位（OSS首位）を記録し、コーディングとエージェント性能を極限まで高めたその実態と、エンジ… h

arXiv:2608.13472v1 Announce Type: cross Abstract: Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition.

arXiv:2608.13547v1 Announce Type: new Abstract: LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot disti

Possibly best way to spend current hour before grabbing 27B model(Instead of opening duplicate repeated 27B posts here). I tried to grab summary(thought of including in this thread) of this video usin

They highlighted 3 things on countdown page: VLM, Agentic Improvements, and Think mode. What improvements do you expect? Reply here! Personally, I want to meet a sage who has attained enlightenment. T

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. @mercor_ai’s @BrendanFoody joined us at our Sovereign AI

I believe the demand for compute is going to go up faster than the supply of compute, so the price of compute is going to increase significantly in the future, perhaps as much as 10x in the next few y

arXiv:2602.24188v2 Announce Type: replace Abstract: We present a scalable and verifiable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games tha

arXiv:2608.10986v1 Announce Type: new Abstract: A growing class of methods probes a language model by feeding it its own output: self-consistency, iterated refinement, agentic loops. We ask what such

arXiv:2608.09857v1 Announce Type: cross Abstract: Advances in advanced artificial intelligence tools have sparked research in robot autonomy, but the development of such systems has largely focused on

arXiv:2608.08648v1 Announce Type: new Abstract: Whole-slide visual reasoning requires identifying sparse diagnostic evidence in gigapixel pathology slides and integrating observations across spatial s

arXiv:2608.09485v1 Announce Type: new Abstract: Cooperative capabilities in language models are dual-use. The same social reasoning that supports civic deliberation can also enable strategic omission,

arXiv:2608.09028v1 Announce Type: new Abstract: Institutional policies stay in natural language while the systems that check compliance demand machine-readable constraints. Bridging that gap is still

really excited to see this release AND integrate it with deepagents!! https://www.langchain.com/blog/switchyard-agent-routing-benchmark Lightning strikes for continuous and long-run agents! Nemotron 3

NVIDIA Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed f

arXiv:2608.07138v1 Announce Type: cross Abstract: Simulated commissioning has become essential for de-risking modern light-source design and commissioning, but the procedures being simulated are still

arXiv:2608.06530v1 Announce Type: new Abstract: Planning a degree from official university sources requires solving two problems in order. The institution's curriculum must first be reconstructed from

Ran the model with quants (Q4) by Unsloth with latest (build from master) llama.cpp server. It takes ~20GB ram running on M5 Pro with 48GB at about 17t/s. Didn't do any reasoning loops/overthinking. O

arXiv:2608.07317v1 Announce Type: cross Abstract: The AI-Native Manifesto envisions large-scale agile software development in which humans increasingly govern intent, risk, and exceptions while agents