Search: “agents”

Gemini Hacked Three Companies in First Known Breakout by Google’s AI Gemini finally caught up on Felony Bench! The hacks, which the company confirmed on Friday, occurred in May as part of a test run b

MiniMax has open-sourced the terminal version of MiniMax Code: https://github.com/MiniMax-AI/minimax-code How can developers verify the content that encoding proxies read, send, and store? This is a t

arXiv:2609.20353v1 Announce Type: new Abstract: We study repeated contract design when a principal observes outcomes but not the actions that generate them. The principal may use any bounded outcome-c

Saw this little dude in a Forbes article (https://www.forbes.com/sites/johnkoetsier/2026/08/18/american-humanoid-robot-launches-for-just-1688-delivery-this-fall-made-in-san-francisco/) This is definit

arXiv:2609.20758v1 Announce Type: cross Abstract: Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in

arXiv:2609.20408v1 Announce Type: cross Abstract: Large language models are usually interpreted through concepts that humans already possess: truthfulness, refusal, deception, personality, harmfulness

arXiv:2609.17800v1 Announce Type: new Abstract: Vision-language models (VLMs) remain largely unreliable on panoramic dental radiographs and can rely on learned anatomical priors rather than evidence i

arXiv:2609.18965v1 Announce Type: cross Abstract: This paper presents BadQubits, an LLM-based framework for static pre-execution detection of structurally harmful OpenQASM 2.0 circuits. The framework

Salut, je cherche de l'aide pour un projet d'IA locale. J'ai un Dell OptiPlex 7070 Micro sous ubuntu server avec un i5-9500T, 32 Go de RAM et aucun GPU (j'en ajouterai un à l'avenir). Je sais que la m

I'm at a crossroads with two grad school options that would take me in somewhat different research directions, and I wanted some general advice on these fields, their growth, and industry alignment. I

arXiv:2609.18908v1 Announce Type: new Abstract: Existing legal benchmarks cover diverse tasks, while continuous monetary remedies remain comparatively underexplored. We introduce ECtHR-NPD, to the bes

arXiv:2609.18274v1 Announce Type: cross Abstract: Classroom observations are widely recognized as a key tool for establishing benchmarks of education quality and guiding pedagogical improvement, yet t

arXiv:2510.08928v2 Announce Type: replace Abstract: Existing benchmarks for large multimodal models (LMMs) often fail to capture their performance in real-time, adversarial environments. We introduce

arXiv:2609.17633v1 Announce Type: new Abstract: The Graph Coloring Problem (GCP) is NP-hard and DSATUR stands as one of the fastest heuristics for it despite producing colorings that typically use mor

OpenAI Group PBC today launched Astra for Law, a version of its GPT-6 Astra model set up for legal research and drafting. Astra for Law is not a new model. The company has wrapped GPT-6 Astra in a leg

OpenAI: OpenAI launches Astra for Law, combining GPT-6 Astra with a legal search index and instructions for legal analysis and writing, initially for select law firms — Our most powerful model, config

Perhaps the most important warning I ever issued was this, to the US Senate, May 2023: “A month after GPT-4 was released, OpenAI released ChatGPT plug-ins, which quickly led others to develop somethin

arXiv:2609.18861v1 Announce Type: new Abstract: Adaptive learning systems commonly formulate learning path planning as Exercise-Centric (EC) recommendation, where the next step is inferred from item-l

arXiv:2609.18440v1 Announce Type: new Abstract: Lindsey et al. (2025) report that Claude 3.5 Haiku plans rhymes: features for candidate rhyme words are active on the newline before a line is written,

arXiv:2609.17542v1 Announce Type: new Abstract: Large language model services increasingly route each query to one of several models of differing capability, using a cheap estimate of query complexity

Schmidhuber was building recursive self-improving systems back in 1987. His new post covers four decades of RSI, from meta-evolution and self-modifying policies to the Gödel Machine and modern LLM age

AIOps (Artificial Intelligence for IT Operations) merges AI and machine learning with comprehensive observability to automate event correlation, root‑cause analysis, anomaly detection, incident respon

arXiv:2609.18731v1 Announce Type: new Abstract: Bridging the gap between human intent and machine execution remains a challenge in automated planning, where expressing goals in formal languages like P

I find another new model at HF: https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B 'Xing4.0-29B-A4B is a next-generation large language model in the Xing series (formerly TeleChat), developed by Chin

arXiv:2609.16592v1 Announce Type: new Abstract: This paper presents an end-to-end approach for generating context-specific large language model (LLM) benchmark datasets by combining expert input with

au revoir, Stainless Building production-level SDKs is extremely important for any developer product, and also really hard. This is a fun post from our engineering team on why there's value in tooling

arXiv:2609.16407v1 Announce Type: cross Abstract: On a delivery platform, personalized store ranking greatly influences what users find and order. Unlike digital-only domains, candidate stores are loc

Hey experts! I genuinely have this question and would love a general consensus from people actually using these models. LLMs have advanced a lot in benchmarks and in practical usage. Even GPT-4o and G

Claude Cowork and chat are now one Claude In hopefully good news for anyone who, like me, was increasingly confused at Cowork v.s. Claude v.s. Claude Code: Starting today, Claude Cowork and chat are m

arXiv:2609.17479v1 Announce Type: cross Abstract: Despite the rapid uptake of black-box object detectors in marine mammal research and monitoring, explainability techniques are rarely integrated into

arXiv:2609.16610v1 Announce Type: new Abstract: Zero-shot waypoint navigation requires vision-language models to select, from the current first-person observation, a sequence of spatial actions that i

AI factories are the infrastructure of the intelligence era. Scaling them responsibly will depend as much on innovation across the grid as inside the data center. Today, Emerald AI, Google and NVIDIA

arXiv:2609.16822v1 Announce Type: new Abstract: This study covers foundational concepts for enhancing plan-execution flexibility, including partial-order planning, the producer-consumer-threat formali

arXiv:2412.00606v2 Announce Type: replace Abstract: Biases in automated clinical decision-making using Electronic Healthcare Records (EHR) impose significant disparities in patient care and treatment

arXiv:2609.17210v1 Announce Type: cross Abstract: Vision-language-action (VLA) models, world-action models (WAMs), and offline reinforcement learning methods are rapidly expanding the design space of

arXiv:2609.17326v1 Announce Type: new Abstract: Scientific poster generation distills a multimodal paper into a single-page visual artifact, forcing strict trade-offs between informational coverage an

GPT-6 Astra is an obviously broken product that needs to be taken off the market until it’s fixed. AXIOS: “.. It's increasingly clear that the Hugging Face breach wasn't a one-off incident.” @inafried

I've been working on something that started as the training backend for my Hierarchos architecture, but it has grown into a much broader project: https://github.com/necat101/Hierarchos-Native Hierarch

Interesting safety paper from Microsoft. They find that a weaker, unaligned model can split a harmful task into harmless-looking subquestions, ask an aligned frontier model each one in a separate sess

arXiv:2609.15994v1 Announce Type: new Abstract: LLMs handle ordinary typing variation fluently: a typo or missing punctuation leaves both user intent and the model's response substantively unchanged.

arXiv:2609.17429v1 Announce Type: cross Abstract: Many learned sequential decision systems map the current state directly to an action. That shortcut becomes brittle when candidate actions are numerou

arXiv:2609.17488v1 Announce Type: new Abstract: We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX

arXiv:2609.16730v1 Announce Type: new Abstract: Conversational memory changes during use, so endpoint question answering alone cannot establish how a persistent state accumulates, ages, or incorporate

My name is Chris Painter, and I'm the President of METR (Model Evaluation and Threat Research). I know we've made a lot of new friends on the internet the last couple of days, so I thought I'd take th

arXiv:2609.17064v1 Announce Type: new Abstract: Assistive autonomous systems must anticipate human goals before an observed behavior is complete. This article formulates anticipation as goal inference

Pipedrive Inc., an intelligent customer relationship management platform for small- and medium-sized businesses, today announced the general availability of Nova, an artificial intelligence tool that