Knowledge catalogue
arXiv:2607.27816v1 Announce Type: new Abstract: Role-playing agents (RPAs) have become one of the most important consumer applications of large language models. Users engage in multi-turn conversation
arXiv:2607.28568v1 Announce Type: new Abstract: Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a
arXiv:2607.28470v1 Announce Type: cross Abstract: Airborne surveillance from low Earth orbit is hindered by two interconnected bottlenecks: nanosatellites have a limited downlink budget, yet the conve
arXiv:2607.26307v1 Announce Type: new Abstract: Contemporary LLM-based coding agents produce code as black-box outputs: the rationale behind each line is hidden, the evolution of the code through benc
We have an idea for dinner 2 already :) But what ideas are you all interested in? - technical topics like rl envs, continual learning, cloud agents, world models - general startup / company building f
arXiv:2607.26115v1 Announce Type: cross Abstract: We introduce extbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal
Interesting data from the OpenRouter Kimi K3 dashboard: @togethercompute offers one of the lowest prices for @Kimi_Moonshot K3 while also achieving one of the highest prompt cache hit rates. Low prici
arXiv:2607.26809v1 Announce Type: new Abstract: General-purpose robotic manipulation requires robots to perform diverse tasks in open-world environments while improving their skills over time. Despite
AI can write more code than any team can review by hand, and a pull request can look fine while hiding a security issue or missing a requirement. In our new short course, AI Code Review, built in coll
This post explains how Private Key JWT client authentication works in AgentCore Identity and reviews the supported grant flows. We then walk through creating an AWS KMS signing key, registering its pu
arXiv:2607.25620v1 Announce Type: new Abstract: Quattrociocchi and colleagues warn that the fluent outputs of large language models may allow linguistic plausibility to substitute for epistemic evalua
arXiv:2607.25637v1 Announce Type: cross Abstract: F(AI)2R is FAIR research with AI in the loop, twice: an AI-assisted authoring pass and a machine-readable audit pass over every artefact. AI systems n
arXiv:2508.21652v2 Announce Type: replace-cross Abstract: Matched filters are widely used to localise signal patterns due to their high efficiency and interpretability. However, their effectiveness de
arXiv:2607.25108v1 Announce Type: cross Abstract: Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, pro
arXiv:2607.24756v1 Announce Type: cross Abstract: What gets lost when memory becomes media? Diaspora oral-history interviews require a double transformation; first-person recollection to third-person
arXiv:2603.08111v2 Announce Type: replace Abstract: Generalizing decentralized multi-robot cooperative transport across objects with diverse shapes and physical properties remains a fundamental challe
arXiv:2607.24482v1 Announce Type: new Abstract: Deploying multiple UAVs for remote sensing enables proportional reductions in mission time, but realizing these benefits requires the fleet to coordinat
arXiv:2607.23442v1 Announce Type: new Abstract: LLM debate is usually evaluated by final answers, but transcripts also reveal whether later turns develop new argumentative content or return to earlier
arXiv:2607.23983v1 Announce Type: cross Abstract: Operational flood forecasting depends on tacit forecaster expertise that is difficult to formalize, audit, and transfer. Although artificial intellige
Our users have been really excited to try Kimi K3 and we're excited to bring it to Augment's product family. It is the most capable open-source model that we have tested to date. Try it today in Cosmo
arXiv:2603.27476v2 Announce Type: replace Abstract: AI-powered people search platforms are increasingly used in recruiting, sales prospecting, and professional networking, yet no widely accepted bench
arXiv:2607.22572v1 Announce Type: new Abstract: Large language models can generate fluent SQL from natural language, but on real enterprise Oracle databases they frequently fail at execution time: col
arXiv:2607.22545v1 Announce Type: cross Abstract: Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, re
arXiv:2607.22371v1 Announce Type: new Abstract: Few-shot learning enables medical image segmentation models to adapt to new tasks using only a small number of labelled examples. However, adaptation pe
Hey folks — I built ContextMemory, an open-source agentic context gateway for apps that already talk to LLMs. The idea is simple: keep your existing POST /api/chat client (Ollama wire format), point i
In partnership with @Kimi_Moonshot, we now have K3 on Together APIs with capacity for hundreds of millions of TPM on launch day! Kimi K3 is now live on Together AI. We’re proud to be a Day 0 launch pa
arXiv:2607.22153v1 Announce Type: cross Abstract: Industrial health management increasingly relies on heterogeneous information sources, including condition monitoring systems, supervisory control and
Kimi K3 is now available on @digitalocean 's Serverless Inference! Developers can start building with our most capable model in minutes. .@Kimi_Moonshot K3 from Moonshot AI is now live on DigitalOcean
Microsoft AI: Microsoft says MAI-Cyber-1-Flash and MDASH, its vulnerability identification harness, deliver “world-class performance at 50% of the cost of leading models” — Today we're announcing MAI-
arXiv:2607.21876v1 Announce Type: new Abstract: We investigate a decentralized reinforcement learning problem involving multiple agents that interact with the same Markov Decision Process (MDP). The a
clem 🤗 on 𝕏: https://x.com/ClementDelangue/status/2081056675558195657 • Radical transparency: let’s release the traces from the “rogue” agents so the entire research community can study what happened.
I was exploring how to prompt the voice chat so that it can correctly count the number of “e”s in seventeen (which it fails most of the time). At the beginning of a new chat, instead of counting “e”s
The Gemma series is an amazing set of highly performant open-weight models. They have proven extremely effective in industrial settings where site-deployed agents need exactly this as a base for domai
mr‑r0b0t announced that Claude Opus 5 is available at a 20 % discount through the Nous Portal. The model can be accessed via the Hermes Agent on the Nous Portal, as well as through OpenRouter and Anth
arXiv:2607.18597v2 Announce Type: replace Abstract: Counterfactual credit assignment has proven effective in multi-agent reinforcement learning (MARL) for discrete action spaces, yet its extension to
arXiv:2607.20498v1 Announce Type: new Abstract: Large language models (LLMs) augmented with tools are emerging as autonomous agents capable of using Web engine, APIs, and code to solve complex, long-h
arXiv:2409.14557v4 Announce Type: replace-cross Abstract: We study a structured class of Markov Decision Processes, known as Exo-MDPs, in which the state space is partitioned into exogenous and endoge
arXiv:2606.14502v2 Announce Type: replace Abstract: Large Language Models (LLMs) are undergoing a fundamental transformation from conversational generators into integrated AI systems capable of reason
This post covers Opus 5’s improvements and practical guidance for AI engineers integrating the model into agentic systems and production inference workloads on Amazon Bedrock. See the documentation fo
arXiv:2607.20430v1 Announce Type: cross Abstract: We present LLM-INSTRUCT, the winning system for the UZH Shared Task at ArgMining 2026 on paragraph-level argument mining in UN and UNESCO resolutions.
NVIDIA ModelExpress (MX) is an agentic AI platform that streamlines the lifecycle of large‑model weights by automatically locating and using the fastest path to load them—prioritizing GPU‑to‑GPU P2P R
arXiv:2607.20549v1 Announce Type: new Abstract: Trajectory datasets used in ADAS evaluation are heavily biased toward routine driving; genuine vehicle-to-vehicle conflict events are rare, and the rare
arXiv:2607.21072v1 Announce Type: new Abstract: Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world. Many spatial tasks a
arXiv:2607.20916v1 Announce Type: new Abstract: Generative AI lets large language models produce scholarly-looking text within seconds, yet fluency does not equal valid explanation. The deepest risk i
AI infrastructure buildouts are moving so fast that plans made just months ago are already obsolete, forcing hardware makers to rewrite how they design, source and ship the systems powering the next g
arXiv:2607.11338v2 Announce Type: replace Abstract: Symbolic expressions can effectively characterize and predict circuit behavior, but deriving them directly from circuit schematics is challenging. T
A Chinese article compiled 52 remarks from Liang Wenfeng’s four-hour investor meeting. I’ve summarised the most important ones below. DeepSeek has one central objective: AGI. This is not the time to m
On July 23, 2026, the user posted a tweet announcing attendance at the “Advancing AI” event hosted by AMD in San Francisco, where Lisa Su would be speaking. The tweet noted the importance of a proper
arXiv:2607.19653v1 Announce Type: cross Abstract: Large language model (LLM) agents now perform well on correctness-oriented repository-level tasks, including SWE-Bench issue resolution and feature im
arXiv:2607.19400v1 Announce Type: new Abstract: Pre-trained foundation models (FMs) have begun transforming single-cell genomics, but scaling them raises privacy concerns. Moreover, unlike text data,
I don’t believe reality is a simulation, but you genuinely couldn’t script this timeline: • Two weeks ago: At @swyx’s AI Engineer World’s Fair in SF, I decide at the last minute to introduce my friend
You can talk to Grok like a person to accomplish tasks via Grok Build http://X.ai/cli I’ve gotten so used to Grok’s speech-to-text that typing now feels like hell Quick tip: Even when you’re using ano
At ChatGPT scale, user frustration arrives as support tickets, ratings, social posts, and corrections buried inside conversations. OpenAI built a feedback system that can find the pattern behind a com
My 2hr workshop on Open vs Closed models, reward hacking, benchmaxxing & RL is out! 1. Closed vs open models 2. Throughput maxxing but accuracy minimizing 3. Benchmaxxing & cheating 4. Distillation &
arXiv:2607.13602v1 Announce Type: cross Abstract: Systematic comparisons between current situations and structurally similar past events in the historical, i.e., historical analogies, is among the mos
arXiv:2607.13054v1 Announce Type: cross Abstract: Environmental monitoring with unmanned aerial vehicles (UAVs) requires route planning methods that maximize covered area while handling energy limits,
arXiv:2607.13072v1 Announce Type: cross Abstract: Zero-shot object-goal navigation aims to enable an intelligent agent to explore and navigate to objects of unknown categories in an unfamiliar environ
It is clear open source models and harnesses are having a moment. There's a few factors at work 1/ It is now obvious that you can catch up to near-SOTA performance and do so with a clear training line
arXiv:2607.14001v1 Announce Type: new Abstract: We suggest using the Lyapunov characteristic exponent (LCE) as a dense reward signal for the reinforcement learning problem of stabilizing the inverted
arXiv:2607.13189v1 Announce Type: cross Abstract: We present RAGthoven, our system for SemEval-2026 Task 1 (MWAHAHA), Subtask A (multilingual constrained humor generation in English, Spanish, and Chin